chore: version packages

Follow-up to #200 and #201, which gate the welcome buttons and the run-mode
dropdown on whether the CLI is actually installed. Four corrections:

1. #200 also DELETED the Cloudflare Tunnel welcome button and the QR widget
   outright. Its rationale is right (offering a tunnel where cloudflared is not
   installed is a bad default) but the conclusion overshoots: the welcome QR is
   the whole scan-to-connect-from-your-phone flow, and deleting it left a large
   block of live tunnel code in settings-ui.js driving elements that no longer
   existed. Both are restored and the button is gated on cloudflared, which is
   what the stated rationale actually asks for. New cloudflared-resolver.ts
   mirrors the CLI resolvers, and TunnelManager now shares its search path so
   the button and the spawn can never disagree about where cloudflared lives.

2. Antigravity was missing from the run-mode gating, the one run mode LEAST
   likely to be installed. It slipped past because #201 predates it. Covered
   now, plus a static test that fails if a sixth mode reaches the dropdown
   without being gated, so the next one cannot slip the same way.

3. The per-surface fetches are replaced by the injected availability object
   already used for the Codex settings tab, so the codebase has one mechanism
   rather than two. The status routes buy nothing as a gating source: every
   resolver memoizes its PATH probe server-side, so a fetch is exactly as stale
   as an injected value while costing a round trip every time the dropdown opens
   and leaving the welcome buttons to flicker in after paint. The routes
   themselves stay, including the /api/claude/status that #200 adds.

4. Unknown availability now reads as AVAILABLE for run buttons. Both PRs hid the
   button on a failed fetch, so a blip left a working install with nothing to
   click; a genuinely missing CLI only ever produced an error toast. The Codex
   settings TAB keeps the opposite default, since hiding it costs nothing.

The dropdown query is also scoped to the menu: `.run-mode-option` is the class
the saved-dashboard and history rows use too, and a document-wide querySelector
would have found whichever came first in the DOM.

Fixes a latent environment-sensitivity in 816d900 while here: the index-title
test asserted the template was untouched apart from the title, which held only
on a machine with no codex installed.

Verified end-to-end against a real server on an isolated instance+socket, with
Playwright: gemini/codex hidden and claude/opencode/antigravity/shell shown,
matching this host, tunnel button back, Codex settings tab still hidden, no
console errors. Full test:ci sweep green (3902 tests).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

.github/SECURITY.md

@@ -4,7 +4,7 @@ Codeman launches AI coding sessions with `--dangerously-skip-permissions`, so th
 web UI is **by design a remote-code-execution surface for whoever can reach it**.
 The entire security model exists to control *who* that is. Please read this before
 exposing an instance beyond `localhost`. The full model lives in
-[`docs/security-architecture.md`](docs/security-architecture.md).
+[`docs/security-architecture.md`](../docs/security-architecture.md).
 
 ## Supported versions
 
@@ -75,4 +75,4 @@ subscribe and send time), and tmux session names discovered on the shared socket
 are validated against the safe-name pattern before reaching any shell call site.
 
 For the detailed rationale, defenses, and recommended secure setups, see
-[`docs/security-architecture.md`](docs/security-architecture.md).
+[`docs/security-architecture.md`](../docs/security-architecture.md).

.github/workflows/release.yml

@@ -52,12 +52,20 @@ jobs:
           OLD_TAG="aicodeman@${VERSION}"
           NEW_TAG="codeman@${VERSION}"
 
-          # Update the GitHub release BEFORE deleting the old tag
+          # Update the GitHub release BEFORE deleting the old tag.
+          # make_latest pins the "Latest" badge to the Codeman release. This repo
+          # publishes TWO packages (aicodeman + xterm-zerolag-input), changesets
+          # creates a GitHub release for each, and GitHub awards "Latest" to
+          # whichever was published LAST. That is a race: 1.9.2 kept the badge,
+          # 1.9.4 lost it to xterm-zerolag-input@0.1.7 by two seconds. All package
+          # releases already exist by the time this step runs, so setting it here
+          # is deterministic.
           RELEASE_ID=$(gh release view "$OLD_TAG" --json databaseId -q .databaseId 2>/dev/null || true)
           if [ -n "$RELEASE_ID" ]; then
             gh api -X PATCH "repos/${{ github.repository }}/releases/${RELEASE_ID}" \
               -f tag_name="$NEW_TAG" \
-              -f name="$NEW_TAG"
+              -f name="$NEW_TAG" \
+              -f make_latest=true
           fi
 
           # Retag

.gitignore

@@ -2,6 +2,9 @@
 .agents/
 skills-lock.json
 
+# Written by install.sh into end-user clones when setup finishes
+.install-complete
+
 # Dependencies
 node_modules/
 
@@ -65,6 +68,9 @@ design-explorations/
 # Artifacts that should not be tracked
 test-results/
 tmp/
+# Machine-local working files (never meant for git). ANCHORED so only the root
+# dir matches.
+/pr/
 # Root `public` (a symlink to scripts/remotion/public — local artifact). ANCHORED
 # with a leading slash so it does NOT also match src/web/public (a bare `public`
 # would swallow the whole web UI source dir and silently un-stage any new asset

.prettierignore

@@ -26,3 +26,6 @@ src/web/public/terminal-ui.js
 src/web/public/voice-input.js
 src/web/public/upload.html
 scripts/remotion/
+
+# Hand-maintained; Prettier escapes underscores in glob paths and corrupts paragraphs.
+CLAUDE.md

.prettierrc

@@ -1,8 +0,0 @@
-{
-  "singleQuote": true,
-  "semi": true,
-  "tabWidth": 2,
-  "printWidth": 120,
-  "trailingComma": "es5",
-  "endOfLine": "lf"
-}

CHANGELOG.md

@@ -1,5 +1,376 @@
 # aicodeman
 
+## 1.10.0
+
+### Minor Changes
+
+- Codeman 1.10.0.
+
+  **Every surface that offers a CLI now checks the CLI is actually there** (#200, #201). The welcome-screen run buttons, the run-mode dropdown and the App Settings "Codex CLI" tab used to be shown unconditionally, so picking one on a box without the binary spawned a session that errored out immediately. All of them now gate on a single server-injected availability object covering Claude, OpenCode, Codex, Gemini, Antigravity and cloudflared, so nothing flickers in after paint and the dropdown costs no round trips to open. Shell is never gated, which is what keeps the menu non-empty on a box with nothing installed, and unknown availability reads as available so a stale page can never leave a working install with nothing to click. Adds `isClaudeAvailable()` and `GET /api/claude/status`, the one CLI that had no availability check despite being the default. The Cloudflare Tunnel welcome button and its scan-to-connect QR are gated on `cloudflared` rather than shown regardless.
+
+  **Shell and remote-SSH sessions now launch a real login shell** (#209, #210). Local shell tabs match what tmux itself does for a pane with no `default-command`, picking up the `/etc/profile` and `/etc/profile.d/*` entries a systemd `--user` service never sourced. On remote SSH, `claude`/`opencode`/`codex`/`gemini`/`agy` are routed through the remote user's interactive login shell, fixing agent CLIs that silently failed with "command not found" because ssh's remote-command execution sees only sshd's minimal default PATH and not the `~/.local/bin` or `~/.opencode/bin` entries where those CLIs actually live. Shell mode uses the remote user's real shell instead of hardcoded bash. The login flags are applied only to shells verified to accept them, so an exotic passwd entry (nushell, elvish, xonsh) cannot produce a dead pane on arrival.
+
+  **A crashed remote pane is kept for diagnosis** (#210), which is how the PATH failure above was found: it previously destroyed the pane, the window and the whole remote session on exit, tearing the local ssh attach down with it and leaving a flap loop with no evidence. Scoped to `remain-on-exit failed`, so a clean `exit` still tears the session down and only a non-zero exit strands anything, and applied last in the tmux command chain so a remote tmux older than 3.2 cannot drop the other session options with it.
+
+  **Resumed sessions under a hidden directory get the right working directory** (#202). Claude Code's project-key encoder maps both `/` and `.` to `-`, and the decoder could not reconstruct a dot-prefixed component, so every session under `~/.codeman` (or any project nested beneath any dotdir) silently resolved to bare `$HOME`. The wrong `workingDir` then propagated into `state.json` and everything trusting it: CLAUDE.md lookup, paste-image directory, subagent and image watchers. A same-named non-dot sibling could also produce a doubled-slash path that failed every later string comparison.
+
+  **Launching a session no longer wipes the terminal you are looking at** (#180). All six run modes route through the shared ownership helpers instead of clearing and writing into whatever session happened to be active, Antigravity included.
+
+  **Codex terminal animations are configurable** (#181), and the App Settings "Codex CLI" tab appears only where the `codex` binary resolves, since both settings on it are handed to `codex` at launch.
+
+## 1.9.9
+
+### Patch Changes
+
+- Two bug fixes.
+
+  **Plain shell sessions could not start when the server process had no `SHELL` (#208).** The tmux pane command for `mode: 'shell'` was the literal string `$SHELL`. That string is embedded in the `bash -c "..."` argument of the `respawn-pane` line, which is run through `/bin/sh -c`, so it was expanded by the _server_ process's shell against the _server_ process's environment rather than inside the pane. Containers and system-level systemd units do not set `SHELL`, so it expanded to nothing and the pane command ended in a dangling `&&`, giving `bash: -c: line 1: syntax error: unexpected end of file` and a pane that died instantly (status 2) while tmux session creation still reported success. The shell is now resolved in Node (`$SHELL`, then the passwd entry, then `/bin/bash`, `/bin/zsh`, `/bin/sh`), requiring an absolute path to an executable and skipping `nologin`-style stubs, then shell-quoted. Only local shell sessions were affected: agent CLI modes emit a real command, and Docker/remote-SSH cases already used a literal `exec bash -l`.
+
+  **A session name typed into the tab options could be silently dropped.** Two independent paths. In the Session Options modal, the Session Name input saves on blur while every autosave handler bails on a null `editingSessionId`, and `closeSessionOptions()` cleared that id before hiding the modal (hiding is what blurs the input), so the save always ran too late; Escape and backdrop-click lost the name with no PUT at all, and only the X button worked because mousedown blurs first. The focused modal field is now blurred before the id is cleared, which also covers the auto-compact prompt. Separately, the right-click inline rename could be destroyed mid-keystroke: the `_inlineRenameActive` guard was missing from `_renderSessionTabsImmediate()`, so a render queued just before the rename opened still rewrote the tab name's innerHTML, committing a truncated name or closing the rename outright. The debounced executor is now guarded too.
+
+## 1.9.8
+
+### Patch Changes
+
+- **Fixed: sessions failed to start on macOS with `Error: posix_spawnp failed.`** (issues #6 and #204)
+
+  `node-pty@1.1.0` publishes its macOS prebuilt helper as `prebuilds/darwin-<arch>/spawn-helper` with mode 0644, i.e. no execute bit. macOS launches every PTY through that helper, so a stock install failed on every session start. The bug is macOS-only: `spawn-helper` is a mac-only gyp target and node-pty ships no Linux prebuild, so Linux always compiles a correctly-permissioned helper from source.
+
+  The previous fix chmodded only `build/Release/spawn-helper`, which on macOS does not exist (the prebuild is used, so node-gyp never runs), and it derived that path from `require.resolve('node-pty')`, landing on `<pkg>/lib/build/Release/...`. It was a no-op on every platform.
+  - New `scripts/fix-node-pty.mjs` (also `npm run fix:node-pty`) chmods every `spawn-helper` it finds, in `build/Release`, `build/Debug` and each `prebuilds/*/`, then verifies the result by actually opening a PTY. A `require()` alone passes on a broken install, because the helper is only touched at spawn time.
+  - `postinstall` no longer force-rebuilds node-pty from source on Node 22+. That step needed Xcode command line tools, cost 30-120s on every install, and deleted the `prebuilds/` tree before compiling, so a Mac without a compiler was left with no working binary at all. A rebuild now happens only when the chmod plus spawn probe still fails, and the prebuilds tree is backed up and restored around it.
+  - New `spawnPtyWithHelperRepair()` (`src/utils/node-pty-repair.ts`) wraps every `pty.spawn()` in `session.ts`, so an install that is already broken repairs itself on the first failed spawn and retries in-process instead of showing a dead session. Unrelated spawn errors are rethrown untouched; a second failure carries the `npm run fix:node-pty` hint.
+  - `scripts/fix-node-pty.mjs` is now in the published `files` list, so global npm installs get the repair too.
+  - Direct-PTY Claude spawns use the resolved absolute binary path (new `getClaudeBinaryPath()`) instead of the bare name `claude`, so a CLI installed outside the server's PATH still launches.
+
+  Verified end to end on macOS 26.4 arm64: a stock `npm i` reproduces `posix_spawnp failed.`, and after the fix the same install spawns a PTY successfully with the prebuilds preserved.
+
+  **Added: phone home screen (session overview)**
+
+  Under 430px the "C" logo now opens a session overview (current sessions, past sessions, spaces) instead of the welcome overlay: on a small screen "which session needs me" beats "how do I start one". Rows resume a session in place, and "New session here" goes through the normal quick-start path so remote and Docker cases keep their routing. Per-device setting `mobileOverviewEnabled` (phones only, default ON) in App Settings. Tablet and desktop are unchanged.
+
+  **Added: guided Tailscale setup in `install.sh`**
+
+  The network-access prompt is now 3-way: Tailscale, LAN, or local-only. The Tailscale path binds loopback and walks through installing Tailscale, logging in, the operator grant, the tailnet HTTPS-certificates toggle, and `tailscale serve --bg <port>`, then verifies the result end to end with curl. That gives HTTPS on a real certificate with no app password and no `0.0.0.0` bind, which is also what PWA install and web push need. `install.sh tailscale` retrofits it onto an existing install, and `CODEMAN_TAILSCALE=1` presets the choice. Serve state is detected from `tailscale serve status --json`; the installer never runs `tailscale serve reset` and never touches serve mappings other than 443 to Codeman's port. README and `docs/security-architecture.md` updated to match.
+
+  **Docs**: replaced a real tailnet hostname with placeholders in `docs/web-tabs-fixes-plan.md`.
+
+  **xterm-zerolag-input**: npm description and keywords only, no code change.
+
+## 1.9.7
+
+### Patch Changes
+
+- Antigravity run mode, plus opt-in entrance animations.
+
+  **Antigravity CLI backend (#207).** Antigravity (`agy`) joins Claude Code, shell, OpenCode, Codex and Gemini as a sixth session backend, following the same pluggable-resolver pattern: `utils/antigravity-cli-resolver.ts` resolves the CLI and `GET /api/antigravity/status` reports availability and path. `ANTIGRAVITY_*` is added to the `ALLOWED_ENV_PREFIXES` allowlist so env overrides stay CLI-scoped rather than blanket-forwarded. Like the other external CLIs it requires tmux with no direct PTY fallback, because secrets are injected through socket-scoped `tmux setenv` and never on the spawn command line. The UI gains a Run-dropdown entry, an agent-type option, an `ag` tab badge and toolbar colours; `runAntigravity()` routes remote and docker cases through `POST /api/quick-start` and skips the local status probe for them.
+
+  **Entrance animations (opt-in, OFF by default).** Optional animations for the four things that appear when work starts: session tabs, the terminal pane a session's CLI runs in, floating agent windows, and the connection lines tying a window back to its parent tab. Defaults are the `legacy` theme, so an untouched install behaves exactly as before and every hook short-circuits on its first line. Choose a look in App Settings > Appearance > Entrance Animations (per-device, stored in localStorage rather than the settings payload); `?animlab=1` opens a per-surface picker with a live preview that fakes tabs, a pane, a window and a line so styles can be compared without spawning sessions.
+
+  Three implementation notes worth knowing if you touch this: tabs and connection lines are destroyed mid-animation on every re-render (`_fullRenderSessionTabs()` replaces the strip's innerHTML, `_updateConnectionLinesImmediate()` clears the SVG), so both are tracked by id and re-applied to the fresh element with a negative `animation-delay` that resumes rather than restarts them; terminal-pane styles animate transform, opacity and clip-path only, because xterm's FitAddon derives rows and columns from the untransformed layout box and animating width or height there would resize the PTY; and window styles that transform also move the rect their connection line aims at, which is why the `beam` style animates opacity and filter only.
+
+  Also fixes an agent window spawning hidden (its agent belongs to a background tab): being `display:none` it never ran its animation, so `animationend` never fired and the entrance class plus its inline custom property stuck to the window permanently. Hidden windows now skip the entrance entirely.
+
+## 1.9.6
+
+### Patch Changes
+
+- Two fixes from community PRs (thanks @Lint111):
+  - fix(transcripts): complete tools from user-entry results (#177). Claude transcripts record tool requests in assistant entries but commonly carry their results in user-role entries; the transcript watcher only completed tools from the older assistant-entry path, so Codeman could keep showing a tool as running after it had finished. The watcher now recognizes `tool_result` blocks in user entries, ends the active tool state, and emits `transcript:tool_end` with the correct tool name and error status. Watcher tests also moved from fixed sleeps to condition-based `vi.waitFor` assertions.
+  - fix(notifications): quiet lifecycle hook noise (#178). Notification preferences move to schema version 5: the drawer-only "Response complete" (stop) default is now off, and the migration disables only the legacy drawer-only shape, preserving any explicit browser, audio, or push delivery the user opted into. Teammate-idle and task-completed hooks now map to the existing opt-in subagent categories instead of the broadly enabled idle/stop alerts, so normal agent activity no longer floods the drawer. Local and server-hydrated preferences are normalized through the same migration path (server hydration used to revive the retired default on fresh browsers), and the notification storage key now uses the stable handheld identity so an unfolded foldable keeps its mobile defaults and storage key (tablets and desktops unaffected).
+
+## 1.9.5
+
+### Patch Changes
+
+- Background-Bash rewake hook, hooks self-heal that preserves user hooks, and test-harness isolation.
+  - New `PostToolUse(Bash)` hook (PR #176): a self-contained `node -e` helper watches the session transcript for a background command's completion notification and uses Claude Code's `asyncRewake` to wake an idle agent (exit code 2), without injecting terminal input that could submit a user's draft. Works on Claude Code 2.1.207+; older CLIs strip the fields harmlessly.
+  - Hooks self-heal (`refreshStaleHookSecret` renamed to `refreshStaleCodemanHooks`) now replaces only Codeman-owned handlers, preserving user events, matchers, and sibling handlers in mixed configurations; `writeHooksConfig` merges instead of clobbering the hooks key at case creation (PR #176).
+  - Rewake helper hardening: self-terminates on its own 6h deadline and when orphaned; the marker is versioned (V2) with a version-agnostic ownership prefix so future script updates replace older handlers instead of duplicating them.
+  - Hook timeout units fixed: the hook `timeout` field is seconds (the CLI multiplies by 1000), so `HOOK_TIMEOUT_MS = 10000` gave curl hooks a ~2.8-hour effective timeout; now `HOOK_TIMEOUT_SECONDS = 10`.
+  - Test-harness isolation (PR #175): every test file gets a temporary `HOME`/`USERPROFILE` so tests cannot touch real Codeman state or delete real case directories, and `Session` attaches a raw-mode echo PTY instead of a real tmux client under Vitest. Fixes the quick-start suite deleting the real `~/codeman-cases/testcase`.
+  - CI stability: drain console-log rpc forwards before worker teardown (fixes a run-failing `EnvironmentTeardownError` with all tests passing); `test/webview-proxy.test.ts` no longer accidentally runs under the jsdom environment via a directive named in a comment.
+  - Release workflow pins the GitHub "Latest" badge to the Codeman release.
+
+## 1.9.4
+
+### Patch Changes
+
+- Fix a latent bug where a partial settings PUT silently reset live service state, and trim the `xterm-zerolag-input` README callout.
+  - **`PUT /api/settings` no longer resets watchers on a partial body.** The three `toggleService` calls (subagent watcher, workflow-run watcher, image watcher) read the raw request body with `??` defaults, so every key a caller omitted was treated as "apply the default". A body of just `{statusLineTelemetry:true}` would START the subagent watcher and STOP the workflow and image watchers, undoing the persisted config. They now resolve from `merged` (persisted settings + incoming), the same convention the `tmuxHistoryLimit` branch in that handler already used, so any PUT reconciles services to the effective stored state. Nothing triggered this in practice because every shipped client sends a full settings payload rebuilt from the DOM, but it was a trap for the next partial-update caller.
+  - **Regression test**: `test/routes/system-routes-settings-partial-put.test.ts` (4 cases) pins both directions, omitted keys preserve state and explicit keys still take effect. Verified to fail against the pre-fix handler.
+  - **CLAUDE.md** records the rule under "Adding Features → App setting": anything acting on a setting in that handler must resolve from `merged`, never the request body.
+  - **`xterm-zerolag-input` README**: removed the links line (getcodeman.com / install one-liner / star link) from the Codeman callout above the demo GIF. The callout keeps its links in the heading and body.
+
+## 1.9.3
+
+### Patch Changes
+
+- Plan-usage chip now defaults ON on desktop, plus the reworked `xterm-zerolag-input` README.
+  - **Plan-usage chip defaults ON (desktop).** The `showPlanUsageLimits` chip (live 5-hour and weekly plan usage from the Claude statusline) used to be opt-in and default OFF, so most users never saw it. Desktop now defaults ON; handhelds still default OFF so the phone header stays minimal and the `mobile-header-buttons-policy` guard keeps passing. Devices with an explicitly stored preference keep whatever they chose, so nobody's OFF gets overridden.
+  - **One resolver behind the chip.** Added `planUsageChipEnabled()` in settings-ui.js and routed all three call sites through it: the App Settings checkbox, the chip's visibility, and the create-time `statusLineTelemetry` flag in session-ui.js. Those three had independent `?? false` / `=== true` defaults, and a chip revealed without the telemetry flag renders `—` forever, so a default flip on one site alone would have shipped a permanently empty chip.
+  - **Cron button comment corrected.** The App Settings comment claimed "Cron button defaults ON" while the code, the template (`btn-cron--hidden`) and the CSS all default it OFF. Verified against a fresh browser profile: the button is hidden and its checkbox unchecked out of the box. Comment now matches, and states why the two halves stay consistent.
+  - **Docs.** CLAUDE.md, `docs/architecture-invariants.md` and `docs/usage-limits-display-plan.md` updated for the new default and the single-resolver rule; the stale `styles.css` comment claiming the server strips the chip's hidden class at render was corrected (display is per-device, so the client reveals it).
+  - **`xterm-zerolag-input` README rework** (0.1.5 shipped the content; this republishes with the graphic and promo changes): replaced the misaligned 8-line keystroke-flow diagram with a two-line stock-vs-zerolag contrast, added a Codeman callout above the demo GIF with links to getcodeman.com and the repo, and rewrote the Origin section so it argues the extraction story instead of repeating the promo.
+
+## 1.9.2
+
+### Patch Changes
+
+- Rewrite the `xterm-zerolag-input` package README as a value-first document and correct the drift that had accumulated against the source.
+  - Added the side-by-side phone demo GIF (`docs/images/zerolag-demo-20260728.gif`) as the hero image, referenced by absolute raw URL so it renders on npmjs.com as well as GitHub. The two-phone comparison shows 0ms local echo next to a 600ms-2.7s server echo on the same session.
+  - New "Why this one" comparison table, an explicit list of target use cases (SSH web clients, cloud IDEs, mobile terminals, container consoles), and a bundle-size badge (6.1 kB gzipped, measured from the ESM build).
+  - Corrected the test-count badge from 78 to the actual 175 tests across 5 files, in both the package README and the Published Packages section of the root README.
+  - Removed the stale "Unicode/emoji rendered at single-cell width" limitation. CJK, fullwidth forms and emoji have had double-width rendering and visual-column positioning since the wide-character fix; the honest remaining caveat (per-code-point width summing over-counts ZWJ grapheme clusters) replaces it.
+  - Documented the previously undocumented public `setPrompt()` method for switching prompt strategies at runtime, and the new "Wide characters (CJK, emoji)" integration section covering the optional `Unicode11Addon` path and the built-in range-table fallback.
+  - Documented `backgroundColor: 'transparent'`, corrected the `foregroundColor` default, and updated the grid-alignment math to reflect visual-column positioning rather than character index.
+
+  No source changes, docs only.
+
+## 1.9.1
+
+### Patch Changes
+
+- Narrow the Run dropdown, and close the last two gaps in web-tab asset rewriting.
+
+  **The Run dropdown was pinned at its full width.** It capped at 300px, and the recent-session rows wanted 326px, so it always rendered at the cap and reached further across the terminal than it needed to. Now 250px, chosen as the width at which a `~/<dir>/<repo>` + timestamp row still fits whole, since identifying a session to resume is what that list is for. Three fixes were needed to make the narrower menu degrade instead of clip: the saved-URL label now has its own element, because `text-overflow` on the row button did nothing (a bare text node inside a flex container becomes an anonymous flex item that ellipsis cannot reach); `.hist-dir` got `min-width: 0`, without which a flex item refuses to shrink below its own text and pushes the date out of the box; and history rows are held to the container width, because the list's `overflow-y: auto` implicitly makes `overflow-x: auto` and let each row size to its own content and scroll sideways. Phone and tablet widths are unchanged, being set separately in `mobile.css`.
+
+  **A dashboard's own `/api/...` assets are relayed again.** The `Referer`-keyed 404 fallback, which rescues a root-absolute asset that no rewrite layer could reach, refused everything under `/api` outright. Dashboards commonly serve their assets from exactly that namespace, so those requests had no rescue at all. The refusal is now precise: the relay runs before the API-shaped 404, and the auth exemption refuses only paths that resolve to a REAL Codeman route, with `/ws/` and `/q/` still refused by prefix.
+
+  Two findings shaped that fence, both from probing Fastify rather than reading it. `hasRoute()` matches the registered PATTERN literally, so `/api/sessions/abc` reports no match against a registered `/api/sessions/:id` and would have granted an unauthenticated exemption on a live session-scoped route; `findRoute()` performs the real lookup and is what the fence uses. And `@fastify/static` is mounted at `/`, so it registers a root catch-all matching every path, which has to count as "no real route" or the fence would refuse every referer-form request and break the rescue that already worked. A root catch-all is distinguishable because it is the only route whose wildcard param comes back equal to the whole request path. The fence fails closed, and both edges are pinned in `test/webview-auth-exemption.test.ts`.
+
+  **`url()` inside runtime CSS is rewritten.** Measuring the fallback against a purpose-built dashboard showed one sink no relay can reach: a `<style>` element built by page script has no URL of its own, so the browser sends an EMPTY `Referer` with the image request it triggers. The injected URL shim now rewrites root-absolute `url()` in `<style>` blocks, both as markup and when a `<style>` node is inserted. Verified in Chromium: a stylesheet-only `/api/hero.png` and a runtime `<style>` `/api/late.png` both load, where both previously failed. The remaining known gap is self-navigation via `location.href`, which cannot be patched because `Location.href` is unforgeable.
+
+## 1.9.0
+
+### Minor Changes
+
+- 2667150: feat(mobile): browse and insert local file and folder paths
+
+  Add a root-confined filesystem picker to Link Existing and the extended mobile
+  keyboard bar. Selected paths remain editable at the active prompt, supported
+  images/documents/text files open in a safe inline preview, and a new one-tap
+  action clears only the current unsent input without invoking `/clear`.
+
+### Patch Changes
+
+- 3cff98f: Fix two multi-user scoping holes in the new filesystem path picker. `GET /api/filesystem/browse` and `GET /api/filesystem/preview` accept an optional `sessionId` that contributes the session's working directory as a browse root, but they resolved it straight off the session map without an ownership check, unlike the nine other session-scoped handlers in the same route file. A non-admin could therefore pin another user's working directory as a root simply by passing their session id, then list and preview files under it. Both endpoints now run `canAccessOwned` and report 404, which also avoids confirming that a session id exists.
+
+  Separately, `Home` and `CASES_DIR` were unconditional browse roots for every caller. Per-user spaces live at `<USER_SPACES_DIR>/<username>`, which is inside `homedir()`, so the `Home` root alone exposed every other user's workspace to any authenticated user. In multi-user mode a non-admin now gets only their own space plus anything explicitly listed in `CODEMAN_FILE_PICKER_ROOTS`; `/mnt/d` is no longer offered by default, since a broad host mount should be an explicit operator decision in a multi-user deployment. Admins keep the host-wide roots, and single-user mode is unchanged.
+
+  Both holes are regression-guarded in `test/routes/file-routes.test.ts`, verified to fail against the previous code. Multi-user mode is opt-in and off by default, so single-user installs were never affected.
+
+- Web tabs: delete saved URLs from the Run dropdown, and fix images in proxied dashboards.
+
+  **Saved URLs are now manageable from the dropdown.** Each row under "Web / URL" gains a gear and an `x`, so a URL can be edited or deleted without first opening it as a tab. Previously the only delete path ran through the gear on an open tab, which was a dead end for a URL you no longer wanted open at all. Both controls stay permanently visible rather than hover-revealed, because the same menu is used on touch, and they get a larger hit box there. Deleting leaves the dropdown open on the remaining rows, and deleting the dashboard that is currently open also closes its tab and unmounts its frame.
+
+  **Runtime-injected images no longer 404.** A dashboard that renders its own markup from script (`card.innerHTML = '<img src="/api/hero?slug=x">'`, `img.src = '/api/slide'`) escaped every rewrite layer at once: `<base href>` never applies to a root-absolute URL, the server-side attribute rewrite only ever sees the initial document, and `runtimeUrlShim()` patched only `fetch`, `XMLHttpRequest`, `WebSocket` and `EventSource`. Those requests landed on Codeman's own root and 404'd, with a symptom that reads as an upstream fault: the dashboard's data loaded while every image stayed broken.
+
+  The shim now also covers the DOM URL sinks, so the request is never emitted in the first place and neither the `/api` fence in the 404 fallback nor the one in the auth middleware had to move. It wraps `innerHTML`, `outerHTML`, `insertAdjacentHTML` (including on `ShadowRoot`), `setAttribute`/`setAttributeNS`, and the `src`/`srcset`/`href`/`poster`/`data`/`action` property setters on img, source, media, video poster, script, iframe, embed, track, link, anchor, area, object and form, with a `MutationObserver` as a last net for sinks not patched above. Every rewrite routes through the same idempotent helper, which matters because unlike the server-side rewrite this one sees markup that may already be proxied, and a page re-injecting its own `outerHTML` would otherwise double-prefix. Everything is defensively guarded and marked so a double injection cannot wrap an already-wrapped setter.
+
+  Measured against a real dashboard: 693 image elements, 0 of them under the proxy prefix and 0 of 23 in-viewport images decoded before, 693 and 23 of 23 after. Covered by a new jsdom suite over the shim's DOM half and a new frontend suite over the dropdown rows. Known remaining gaps are documented in `docs/web-tabs.md`: a root-absolute `url()` inside a stylesheet injected at runtime, and self-navigation via `location.href`, which cannot be patched because `Location.href` is unforgeable.
+
+  Also in this release: a value-first README overhaul pointing at getcodeman.com, and the QR-auth distribution test now uses a chi-square check instead of a max-deviation threshold that failed on random variance.
+
+- bca56b4: Normalize Claude conversations in the response viewer. A Claude transcript is an append-only event log, so one logical exchange spans many JSONL rows: tool-result rows, meta/image/skill rows, compact summaries, task and team notifications, sidechains, replayed assistant snapshots, and multi-block assistant output. The viewer rendered a card per row, which produced duplicate and truncated cards that read as lost responses. Cards are now built at real human-turn boundaries, replayed assistant snapshots are deduplicated, and sidechain rows (which belong to subagents, not the main conversation) no longer leak in. An identical prompt that legitimately recurs after an assistant reply is still kept as its own turn.
+
+  Measured over 40 real transcripts: 3108 cards became 621, duplicate cards dropped from 74 to 8 (all of them genuinely repeated turns), no assistant text was lost, and the non-`context=full` last-response text was byte-identical on every file.
+
+  Also rebinds recovered sessions to their transcript. `reconcileSessions()` can recover a lost mux session as a `restored-<uuid8>` placeholder with a stale working directory, which made transcript lookup by cwd find nothing. The placeholder still carries the first eight characters of the conversation UUID, so the viewer now rebinds to the matching top-level transcript when exactly one candidate matches.
+
+## 1.8.3
+
+### Patch Changes
+
+- 8c089a4: Add four light UI and terminal skins: Paper Gray, Solarized Light, Catppuccin Latte, and Rosé Pine Dawn. The Skin picker now groups Light and Dark options, and each light skin ships a matching xterm ANSI palette plus `color-scheme: light` so native selects, date pickers and scrollbars stop rendering as dark OS widgets on a light page. Terminals set `minimumContrastRatio: 4.5` under a light skin (main terminal and teammate terminals both), which keeps CLI output that assumes a dark background readable, and `applyTerminalSkin()` now refreshes the zero-lag input overlay so typed-but-unflushed text does not keep the previous theme's colors.
+
+  Elevated surfaces (modals, command palette, dropdowns, subagent and ultracode windows, file preview, attachment tray, mobile sheets) now resolve through shared `--floating-bg` / `--control-*` / `--banner-bg-*` / `--modal-backdrop` / `--elevated-shadow` tokens instead of hardcoded near-black rgba, so they follow whichever skin is active. On the Daylight skins this lifts modals slightly off the page background; OG Codeman pins its own near-black value to keep that palette neutral.
+
+  Also defines twelve CSS compatibility aliases (`--bg-primary`, `--bg-secondary`, `--bg-tertiary`, `--text-primary`, `--text-secondary`, `--border-color`, `--accent-color`, `--success`, `--error`, `--danger`, `--font-mono`, `--shadow-lg`) that panels and overlays already referenced in about 79 places but which were never actually declared, so those rules silently resolved to nothing. Status badges and accent-tinted pills (search filter chips and result badges, session tab mode pills, respawn state, Ralph priority and circuit-breaker badges, tunnel and voice status, mobile case picker) no longer keep their pale light-on-dark ink under a light skin, where it measured 1.0 to 1.9:1 and made the search filter chips invisible.
+
+  New static regression `test/skin-themes.test.ts` guards the four-way parity between the CSS token block, the xterm palette, the pre-paint allowlist and the Settings picker.
+
+## 1.8.2
+
+### Patch Changes
+
+- Web tabs: open dashboard URLs as tabs beside agent sessions, plus terminal link fixes.
+
+  **Web tabs.** The Run dropdown gains a "Web / URL" section. A saved URL renders as a tab in the same strip as Claude/Codex/Gemini sessions, with the same Alt+1-9 numbering, an icon picker, and per-device tab order. Frames stay mounted while hidden (LRU-bounded), so switching tabs never reloads a dashboard.
+
+  Dashboards are proxied through Codeman's own origin, because a direct iframe fails three ways at once: an HTTPS Codeman cannot embed a plain-HTTP target (mixed content, with no override at all on iOS Safari), many dashboards send `X-Frame-Options: DENY`, and Codeman's own `default-src 'self'` CSP blocks cross-origin frames. Proxying dissolves all three and leaves the production CSP unchanged. The fetch happens server-side, so a tailnet-only or localhost-only dashboard is reachable from any device that can reach Codeman.
+
+  The proxy is not an API surface: it authenticates on a 192-bit capability in the path (memory-only, rolling TTL, bound to the minting user, revoked on edit or delete) and is exempt from the cookie and Origin checks, because a sandboxed iframe is opaque-origin and sends neither. The Host allowlist is never bypassed. Iframes omit `allow-same-origin` unless a URL is explicitly marked trusted, and `Authorization` plus the session cookie are stripped upstream in both modes so `CODEMAN_PASSWORD` cannot leak into a dashboard. Includes an HTTP and WebSocket proxy, redirect/cookie/`<base>` rewriting, a runtime URL shim for requests built by dashboard JavaScript, and CORS handling for the opaque-origin frame. New endpoints under `/api/webviews`, storage in `~/.codeman/webviews.json`, user guide in `docs/web-tabs.md`.
+
+  **Terminal links no longer truncate.** Three separate cuts, each producing a link that opened the wrong target or none at all:
+  - A single `&` ended the match, so every query string was cut. A WordPress edit link resolved to `?post=1479` and Claude Code's own `/login` URL was unusable. `&` is now part of a URL while `&&` remains a boundary.
+  - Links wider than the terminal were cut at the row boundary. The link provider now stitches continuation rows into one logical line and maps offsets back across rows. Handles both soft wraps (emulator, `isWrapped`) and hard wraps (a program wrapping its own output and emitting a newline, as Ink does), the latter being why the `/login` URL grew longer as the window was widened.
+  - Image and PDF paths were not matched at all, so pasted-screenshot paths rendered as plain text. They now link and open the file preview, which renders images inline.
+
+  **Also fixes** a pre-existing bug where `.toolbar`'s `backdrop-filter` created a stacking context that trapped the Run menu's z-index, letting the welcome overlay cover it: with no session open, every item in that menu (Claude Code included) was unclickable.
+
+## 1.8.1
+
+### Patch Changes
+
+- Mobile toolbar: a dedicated Enter button, and Shell moves into the Run dropdown.
+
+  Submitting is a constant need on a touch keyboard, so on phones (≤430px) the toolbar slot that held "Shell" now holds a dark blue **Enter** button. Starting a shell, the far rarer action, moves into the expandable Run dropdown as `Terminal / Shell` (the Run button then reads "Run SH"). Desktop and tablet are unchanged: the green Run Shell button stays exactly where it was.
+
+  Enter is replayed through the terminal's own input path rather than posted to the input API. This matters because local echo is on by default on touch devices: the characters you type are buffered client-side and have not yet reached the PTY, so sending a bare carriage return would submit an empty line and leave your text stranded on screen. Replaying the keypress flushes the buffered text first, then submits.
+
+  Installer: re-runs and updates now preserve the existing network binding instead of silently reverting it, so upgrading no longer changes how the dashboard is reachable.
+
+  Default desktop header is cleaner: the file viewer is shown by default and the plan-usage chip is unchanged, while the token-count chip and lifecycle-log button now default off. Stored preferences are still honored.
+
+  Docs and repo housekeeping: fresh phone screenshots and a new hero GIF in both READMEs, contributor and total-commit badges, and a much shorter repo root. `SECURITY.md` moved to `.github/` (GitHub resolves it there, so the Security policy tab is unaffected), `SPEEDRUN.md` to `docs/`, the knip config to `config/`, and Prettier's config into the `"prettier"` key of `package.json`. `CLAUDE.md` was split so the always-loaded guidance is roughly half its former size, with the deep implementation detail preserved verbatim in `docs/architecture-invariants.md`.
+
+## 1.8.0
+
+### Minor Changes
+
+- Installer: choose your network binding, with LAN access as the new guided default.
+
+  The install script now asks at the end of setup how the dashboard should be reachable:
+  1. Any device on your network (0.0.0.0), the default. The installer prompts for a dashboard password (hidden input, confirmed twice); declining a password requires an explicit confirmation and the install ends with a prominent warning explaining the exposure.
+  2. This machine only (127.0.0.1), the safer option for tunnel/Tailscale setups.
+
+  The choice is wired into the generated systemd unit and launchd plist (values escaped for each format), the run-now launch path, and the printed URLs, which now include the detected LAN IP for instant phone access. Non-interactive installs keep the safe loopback default unless CODEMAN_HOST is preset, and the server binary's own default binding (127.0.0.1) is unchanged, so npm and manual installs behave exactly as before. New installer env presets: CODEMAN_HOST and CODEMAN_PASSWORD skip the prompts for automation.
+
+## 1.7.1
+
+### Patch Changes
+
+- Mobile and UI polish plus docs refresh.
+  - Mobile: the header brand collapses to a single "C" home button on phones (<430px), freeing header space for session tabs while keeping the same tap target. The compact letter lives in its own span so i18n custom branding keeps rewriting only the full wordmark.
+  - UI fix: the absolutely-centered toolbar voice button no longer overlaps the case picker's chevron and "+" button. Below ~1500px (or with long case names widening the left toolbar group) it now falls back into normal flex flow where overlap is impossible; wide viewports keep the centered layout.
+  - Docs: README gains a hero pitch block with deep links, npm version + GitHub stars badges, and a star CTA; CLAUDE.md core-files table synced (Infra docker modules, app.js line count); blog article images added under docs/images/blog/.
+
+## 1.7.0
+
+### Minor Changes
+
+- Community release (thanks @shenlvkang-collab for all four PRs) plus documentation fixes.
+  - fix(mobile): per-device settings now key off a stable handheld classification (`MobileDetection.isHandheldDevice()`: touch plus UA form-factor tokens, with User-Agent Client Hints fallback) instead of the instantaneous viewport width, so an Android foldable that unfolds past the desktop breakpoint keeps `codeman-app-settings-mobile` and opt-ins such as the Response Viewer and Extended Keyboard Bar. Responsive layout stays width-driven. Adds an OPPO Find N5 (unfolded) device profile and a fold/unfold/reload Playwright regression test (mobile suite now 136 devices). (#162)
+  - fix(paths): `SAFE_PATH_PATTERN` now accepts Unicode letters and numbers (`\p{L}\p{N}` with the `u` flag), so working directories like `/mnt/d/AI/中文项目` validate in Create Session, Quick Run, and Scheduled Run. All shell-metacharacter, traversal, and absolute-path protections are unchanged. (#163)
+  - fix(ui): newly created run sessions render their tab immediately instead of waiting for the `session:created` SSE event (idempotent upsert from the POST response, with a `GET /api/sessions/:id` fallback for quick-start modes), and the Run button holds an in-flight lock (min 500 ms) so a double click cannot create duplicate sessions. (#164)
+  - feat(ui): the synced custom display name and per-device English/Simplified Chinese UI language are described in their own entry (#165); on top of that PR, `renderIndexHtml` no longer recomputes `windowTitle` on solo-session renders, so a detached window cannot reset the push-notification `hostTitle` prefix to the default name.
+  - docs: corrected the `sse-events.ts` fileoverview breakdown (148 event constants, was stale at 120; per-category counts refreshed, including Cron, Docker, Remote auto-reconnect, and Multi-user) and the CLAUDE.md SSE registry count; READMEs synced with the 1.6.2 installer behavior.
+
+### Patch Changes
+
+- 8d9fc41: Add a synced custom display name and a per-device English/Simplified Chinese browser UI language picker under App Settings → Display.
+
+## 1.6.2
+
+### Patch Changes
+
+- Installer (install.sh) reliability and safety overhaul, prompted by a review of the Linux flow:
+  - Install-completion marker (`.install-complete`): a bare re-run only takes the quiet update path when a previous install actually finished. Previously, a first install that failed during npm install/build (or was interrupted) left `.git` behind, so the retry silently became an "update" and the user never got the launch menu, the `codeman`/`tmux-chooser` symlinks, the PATH entry, or the `sc` alias. The marker is refreshed by updates and cleared by uninstall when the app dir is kept; added to .gitignore for end-user clones.
+  - `update` no longer runs an unconditional `git reset --hard` over local changes: interactive runs are asked to stash (declining keeps everything and skips the update), headless runs auto-stash with a dated message (same policy as scripts/self-update.sh).
+  - Service setup is verified instead of asserted: after starting codeman-web, the installer polls `systemctl --user is-active` (up to 6s) and only then prints "Codeman is running now!"; failures print an honest warning plus status/journalctl hints. Uses `restart` instead of `start` so re-running the installer over an already-running service actually loads the new build. A missing user D-Bus session (e.g. bare `ssh host 'curl | bash'`) is detected up front with copy-paste recovery commands instead of dying mid-setup via `set -e`. macOS gets the equivalent `launchctl list` verification, and the update path verifies its service restart too. The Cloudflare tunnel-service offer is skipped when service setup failed.
+  - Headless consent guard: with no interactive terminal AND no explicit `CODEMAN_NONINTERACTIVE=1`, the installer now refuses (with instructions) to run sudo package installs (git/node/tmux) or third-party `curl | bash` AI CLI installers, instead of silently taking the default-yes prompts. Explicit `CODEMAN_NONINTERACTIVE=1` keeps the previous full-auto behavior for CI/automation.
+  - AI CLI gate now recognizes Codex and Gemini (search paths mirrored from the CLI resolvers), so a box with only Codex or Gemini installed is no longer forced to install Claude Code/OpenCode. The install menu gains a "Skip" option (with npm install hints for Codex/Gemini), and the final reminder lists all four CLIs.
+
+  Docs: CLAUDE.md documents `src/remote-reconnect.ts` (pure COD-108 auto-reconnect backoff/eligibility logic) in the Infra table and the remote-sessions pattern.
+
+## 1.6.1
+
+### Patch Changes
+
+- **Admin Panel for multi-user mode.** Admins in multi-user mode now get a prominent Admin Panel button at the top of the page (header, admin-only; the template ships it hidden and `admin-ui.js` reveals it after identity boot; hidden on phones per the mobile header policy, where user management stays reachable via App Settings > Users). It opens a full Admin Panel modal: a users table with role, enabled/disabled status, bypass-permissions grant, live sessions, active logins, case count, and last login; per-user actions for Promote/Demote, Enable/Disable, Grant/Revoke bypass, Reset password (copyable one-time password), Force logout, and Delete (with an optional "also delete their files" step); and a proper add-user form (role, optional password, bypass checkbox) replacing the old prompt() flow. Each user's cases open in a drawer listing their case folders (modified date, live-session badge) with per-folder delete. Two new admin endpoints back this: `GET /api/admin/users/:username/cases` and `DELETE /api/admin/users/:username/cases/:caseName`, guarded like `deleteUserSpace` (symlinks refused, realpath confined to the user's space, folders in use by a live session refused with 409, audit-logged). The panel and the App Settings Users tab live-refresh on the SSE `admin:usersChanged` event (now wired in app.js). New coverage in `test/admin-routes.test.ts` (list/delete, traversal + symlink refusal, non-admin 403) and `test/admin-ui.test.ts` (button reveal gating, panel render, case drawer); verified end to end against a live multi-user instance with curl and Playwright.
+
+  **Also in this release:** README/docs synced with 1.6.0 (remote SSH cases, session manager, permissions) and fixed installer prompts when run via `curl | bash`.
+
+  **Recap of the recent feature line, for readers catching up:**
+  - **Multi-user mode (shipped 1.5.0, opt-in `--multiuser` / `CODEMAN_MULTIUSER=1`).** Named users with scrypt-hashed passwords, per-user case spaces under `~/codeman-users/<name>/cases`, and full ownership scoping of sessions, cases, cron jobs, scheduled runs, search, file previews, and SSE/WS streams. Non-admin users default to Claude's classifier-guarded `--permission-mode auto`; shell mode, cron `launchCommand`, and skip-permissions bypass switches require the per-user `canBypassPermissions` grant (now toggleable from the Admin Panel). Admin API with one-time passwords, last-admin invariants, and an append-only audit log; self-service `/api/me` password change; `codeman users add|passwd|list|rm` CLI. Off by default is byte-identical to single-user. Note: multi-user separates workspaces for a trusted team; it is not a security boundary (all sessions share the host OS account), so pair it with Docker cases for real isolation.
+  - **Docker cases (shipped 1.4.0/1.4.1).** A case can run inside an isolated per-case container (any of the five CLI backends), with one-click "Run in Docker" quick-create, durable in-container tmux that survives Codeman restarts and resumes conversations after container stops, hardened container creation (cap-drop ALL, no-new-privileges, non-root, memory/pid limits, never privileged, never the docker socket), commit-safe seeded credentials, config-drift detection, GPU passthrough, and portable export/import bundles to move a whole case between machines.
+  - **1.6.0 highlights.** Remote SSH cases with durable remote tmux (survives SSH drops, auto-reconnect, shared multi-client attach, discover + attach with detach-not-kill); the Cmd+K session palette and unified Session Manager with pinning, cross-device tab order, and first/last prompt search; full-scrollback replay; and the multi-user permission downgrade now threading through to remote launch/attach.
+
+## 1.6.0
+
+### Minor Changes
+
+- Remote tmux durability, Session Manager polish, and an opt-in Cron button.
+
+  **Remote sessions: durability, discovery, and auto-reconnect** (PR #156 by @aakhter, COD-104 to COD-109)
+  - Durable remote launches survive an SSH drop: the agent runs inside `tmux -L codeman-remote new-session -A` on the remote host, and reconnecting lands back in the same session.
+  - Discover + attach: a "Discover existing sessions" action per remote host lists `codeman-*` tmux sessions on the host's canonical socket (started by the remote's own Codeman or another instance) and attaches to one. Attached (non-owned) sessions detach on tab close, never kill; a structural early-return in `killSession()` guarantees no remote `kill-session` can ever be issued for a session Codeman doesn't own (COD-105).
+  - Shared/collaborative sessions: per-session `window-size latest` so concurrent clients at different viewports don't clamp each other, plus a "shared - N clients" badge in discovery results (COD-106).
+  - Auto-reconnect watcher: a bounded-backoff (5s to 5m, ~6 attempts) watcher detects a dead remote pane and reattaches the still-running remote tmux session; intentional kills/detaches are guarded and never revived. Kill-switch setting `remoteAutoReconnect` (default on). SSE `remote:sessionDropped`/`sessionReconnected`/`reconnectExhausted`, with a manual Reconnect toast after exhaustion (COD-108).
+  - Owned durable sessions propagate `kill-session` to the remote on close (COD-109); the remote tmux prereq probe is skipped under the test runner (COD-104).
+  - All ssh command lines continue to flow through the single shell-safe `buildSshConnectionArgs()` (COD-107). New design doc: `docs/remote-sessions.md`.
+  - Maintainer additions: the discovery endpoint is admin-gated in multi-user mode, and the remote launch/attach chooser threads the multi-user permission downgrade (`claudeMode`/`allowedTools`) through to the remote agent.
+
+  **Session Manager: pinning, cross-device ordering, name/prompt retention** (PR #157 by @aakhter, COD-131/139/140/142/143/145)
+  - Session pinning: pin a session to the top of the Session Manager list (`POST /api/sessions/:id/pin`, `session:pinned` SSE, amber highlight + pin glyph). Pinned group orders most-recently-pinned first (COD-139).
+  - Pinned sessions survive kill: killing a pinned session demotes its record to a lightweight stopped entry instead of removing it, so it stays visible and resumable; cleanup skips pinned records (COD-142). The pin route also works on these persisted-only records, so a pinned-then-killed session can always be unpinned.
+  - Cross-device tab order: tab order syncs via server state (`PUT /api/session-order`, `session:orderChanged` SSE, persisted in `state.json`); the pushing device wins and server-only ids fall to the end, never dropped (COD-131).
+  - Resuming from the Session Manager keeps the session's original name instead of always synthesizing a fresh `w<N>-<dir>` one (COD-143).
+  - firstPrompt backfill for sessions whose Codeman id is not the transcript UUID (claudeSessionId join, then newest transcript in the same workingDir), and the most recent prompt is shown alongside the first and included in search (COD-140/145).
+
+  **Cron button now opt-in** (hidden by default)
+  - The Cron footer-toolbar button follows the same opt-in pattern as the Session Manager / Away Digest / File Viewer buttons: hidden by default, enable per device under App Settings -> Display -> Header Displays. Cron jobs themselves are unchanged.
+
+  Also: `docs/remote-sessions.md` synced with the shipped `-L codeman-remote` / `codeman-ssh-<id8>` naming.
+
+## 1.5.1
+
+### Patch Changes
+
+- Docker session-mode deep-review fixes — the work intended for the skipped **1.4.2**, now merged onto the 1.5.x line — plus a recap of the multi-user mode shipped in 1.5.0.
+
+  **Docker resume actually works now.** `DockerCase.lastClaudeSessionId` was read at quick-start but never written, so the documented resume-after-container-stop never fired. Claude-mode docker panes now pin a deterministic conversation id (`claudeDockerPaneCommand()`): a fresh launch runs `claude --session-id <id> || claude --resume <id>` (a duplicate `--session-id` exits 1 "already in use", so the fallback resumes after a container stop/reboot — verified CLI behavior), an explicit resume runs `--resume <rid> || --session-id <sid>` so a stale id never dead-panes. The id is persisted at launch and again on hook / last-response conversation-id adoption. Verified end-to-end across a `docker stop` + relaunch and a full container recreate.
+
+  **Config-drift detection + recreate (was documented but entirely missing).** The `codeman.confighash` label was stamped but never read, so docker-host config edits silently never applied. Quick-start now compares via `checkDockerConfigDrift()` and refuses a drifted launch with `CONFLICT`; the UI confirms and calls the new `POST /api/docker-cases/:name/recreate` (refused while the case has live sessions), then relaunches with the new config. New SSE event `docker:containerRecreated`.
+
+  **Model picker now applies to docker sessions.** `modelOverride` was absent from `QuickStartSchema`, so the App Settings Claude Model choice was silently inert for docker runs. It is now accepted and applied via `updateCaseModel` for local and docker quick-starts (still rejected for remote, where the settings file would land on the wrong machine).
+
+  **Import hardening.** `importDockerBundle` validates the untrusted cross-machine manifest before trusting any field (`validateImportManifest`: engine/image/containerWorkdir/network/caseName/schemaVersion — a hostile `engine` could previously select the probe binary); the outer bundle tar gets the same member-traversal guard as the inner workspace tar; the quarantine image tag derives from the schema-validated case name.
+
+  **Remote-daemon correctness.** All docker probes and the base-image auto-build now honor a host's `context`/`daemonHost` (`dockerEngineArgv`) instead of always probing the local daemon.
+
+  **Smaller fixes:** commas are rejected in docker workspace/workdir/destination paths (a comma corrupts the `--mount type=bind,src=…` CSV spec, which shell escaping cannot protect); a dead `this.escapeHtml` reference in the exports refresh is fixed; `docker:importComplete` / `docker:containerRecreated` get frontend SSE listeners so other open tabs refresh; the File Viewer header button is hidden on phone headers like its siblings.
+
+  **Docs.** CLAUDE.md + READMEs synced with the current feature set, including a full zh-CN README re-translation.
+
+  **Multi-user mode (recap — shipped in 1.5.0).** Opt-in named users (`--multiuser` / `CODEMAN_MULTIUSER=1`, off by default) with per-user case spaces and full ownership scoping of sessions, cases, cron jobs, scheduled runs, search, file previews, and real-time SSE/WS streams. Non-admin users default to Claude's classifier-guarded `--permission-mode auto`; raw shell mode, cron `launchCommand`, skip-permissions, and the Codex/Gemini bypass switches require an explicit per-user `canBypassPermissions` grant. Machine-level resources are admin-only. Admin API (`/api/admin/users*`) with one-time passwords, last-admin invariants, and an append-only audit log; self-service `/api/me` + password change; and a `codeman users add|passwd|list|rm` CLI. Off by default is byte-identical to single-user. Note: multi-user separates workspaces for a trusted team; it is not a security boundary between mutually-distrusting users (all sessions share the host OS account) — pair with Docker cases for real isolation.
+
+## 1.5.0
+
+### Minor Changes
+
+- 0ab2416: Opt-in multi-user mode (`--multiuser` / `CODEMAN_MULTIUSER=1`, off by default).
+
+  Named users with individually scrypt-hashed passwords in `~/.codeman/users.json`, per-user case spaces under `~/codeman-users/<name>/cases`, and ownership scoping of sessions (create/list/delete/mutate, incl. bulk delete), cases, cron jobs + run history, scheduled runs, search, file previews, session history, away digest, subagent/workflow monitors, and real-time SSE/WS streams (including the debounced session/task update path, clipboard, and push notifications). A non-admin's `workingDir` is realpath-confined to their own space at every spawn/link path (session create, quick-start, cron create/fire, scheduled runs, case link/docker-link, docker import). Non-admin users default to Claude's classifier-guarded `--permission-mode auto`; raw shell mode, cron `launchCommand`, skip-permissions, and the Codex/Gemini bypass switches require an explicit per-user `canBypassPermissions` grant (enforced at every spawn site incl. one-shots, plan generation, scheduled runs, and remote launches). Machine-level resources (remote/Docker hosts + host reads, mux sessions, orchestrator, tunnel, self-update, settings) are admin-only. Admin API (`/api/admin/users*`) with one-time passwords, last-admin invariants (validated before any teardown), and an append-only audit log; self-service `/api/me` + password change; a frontend admin Users tab + change-password modal; and `codeman users add|passwd|list|rm` CLI. Also adds a global `auto` Claude startup permission mode. When off, behavior is byte-identical to single-user.
+
+  Auth hardening: the login throttle verifies the password before consulting the per-account failure bucket (a correct password can never be locked out); the `mustChangePassword` lockbox covers the WebSocket terminal; the cookie fast-path re-validates identity against the store each request (so a CLI/admin delete/disable/demote takes effect promptly); a role/grant change revokes the target's sessions. (Known limitation: a bare CLI `codeman users passwd` reset — no delete — does not by itself revoke an already-active cookie until it expires; use `codeman users rm`, the admin API, or a restart to force-revoke.) Data-integrity hardening: the store distinguishes a missing users file from a corrupt/unreadable one (so a transient read error can't overwrite all accounts) and writes via a unique per-process temp file; the earlier fire-and-forget `touchLastLogin` corruption race is serialized.
+
+  Note: multi-user mode separates workspaces for a trusted team; it is not a security boundary between users (all sessions share the host OS account). Pair with Docker cases for real isolation.
+
+## 1.4.1
+
+### Patch Changes
+
+- **Docker session mode** hardening + fixes, plus a File Viewer header button.
+
+  **What Docker session mode is** (recap): a case can run inside an isolated, hardened Docker container instead of on the host, and any of the CLI backends (Claude, Codex, Gemini, OpenCode, or a plain shell) runs inside it. It is a location overlay on cases — not a new session mode — and the container analog of remote-SSH cases: a local tmux pane `docker exec`s into a durable in-container tmux, with exactly one long-lived container per case that multiple sessions share. The workspace, credentials, and conversation transcripts are bind-mounted so the agent is authenticated and resumable; containers are hardened by default (`--cap-drop ALL`, `--security-opt no-new-privileges`, non-root, pids/memory caps, `--init`, never `--privileged` or the docker socket) and export-safe. Start one with the one-click "Run in Docker" checkbox on Create Case, or the Docker tab for full control.
+
+  This release fixes the rough edges found running it for real:
+
+  Docker cases:
+  - **Seamless Claude auth in containers**: `~/.claude.json` is no longer bind-mounted as a single file (a mount point that broke Claude's atomic-rename config writes — forcing re-auth and, via failed in-place writes, corrupting the host `~/.claude.json`). It is now seeded as a writable, onboarding-complete copy, so a docker session boots straight to the prompt (no theme picker, login, or folder-trust prompt).
+  - **Claude-state isolation**: containers no longer bind-mount the whole `~/.claude` directory (which wrote backups/tasks/teams/settings back into the host). Only `~/.claude/projects` transcripts are shared (host watchers + `--resume`); credentials, settings, and stats-cache are seeded as writable copies; everything else stays container-local.
+  - **Codex/Gemini/gcloud/opencode isolation**: same treatment — codex shares `sessions/` + `history.jsonl` (response-viewer + resume) and seeds `auth.json`/`config.toml`; gemini/gcloud/opencode are whole seed-copies. Containers never write their credential state back into the host dirs.
+  - **Base image auto-builds on first use**: a missing `codeman/agent:base` no longer blocks case creation or launch; it builds locally on first use (concurrency-safe, with SSE progress toasts).
+  - **UTF-8 locale**: containers set `LANG`/`LC_ALL=C.UTF-8` so tmux renders Claude's box-drawing correctly (fixes `qqqq` line artifacts).
+  - **Create Case UI**: larger, collapsed-by-default "Run in Docker" settings with a shorter hint; dockerized cases show a short `(docker)` tag (or the custom host id) in the case menus.
+  - **Tab naming**: docker/remote (and codex/gemini/opencode) sessions now follow the `w<n>-<case>` convention instead of `codeman-<id>`.
+
+  Other:
+  - **File Viewer header button** (opt-in via App Settings, Header Displays): toggle the file browser panel from the header.
+  - Fixed a timezone-boundary flaky test in the away-digest route suite.
+
 ## 1.4.0
 
 ### Minor Changes

README.md

@@ -5,7 +5,7 @@
 <h2 align="center">Mission control for AI coding agents</h2>
 
 <p align="center">
-  <em>Claude Code &bull; OpenCode &bull; Codex &bull; Terminal - One Dashboard &bull; Any Device</em>
+  <em>Claude Code &bull; OpenCode &bull; Codex &bull; Gemini &bull; Terminal - One Dashboard &bull; Any Device</em>
 </p>
 
 <p align="center">
@@ -13,7 +13,10 @@
   <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/Node.js-22%2B-22c55e?style=flat-square&logo=node.js&logoColor=white" alt="Node.js 22+"></a>
   <a href="https://www.typescriptlang.org/"><img src="https://img.shields.io/badge/TypeScript-5.9-3b82f6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript 5.9"></a>
   <a href="https://fastify.dev/"><img src="https://img.shields.io/badge/Fastify-5.x-1e3a5f?style=flat-square&logo=fastify&logoColor=white" alt="Fastify"></a>
-  <img src="https://img.shields.io/badge/Tests-2861%20total-22c55e?style=flat-square" alt="Tests">
+  <a href="https://www.npmjs.com/package/aicodeman"><img src="https://img.shields.io/npm/v/aicodeman?style=flat-square&label=npm&color=22c55e" alt="npm version"></a>
+  <a href="https://github.com/Ark0N/Codeman/stargazers"><img src="https://img.shields.io/github/stars/Ark0N/Codeman?style=flat-square&color=eab308" alt="GitHub stars"></a>
+  <a href="https://github.com/Ark0N/Codeman/graphs/contributors"><img src="https://img.shields.io/github/contributors/Ark0N/Codeman?style=flat-square&color=3b82f6" alt="Contributors"></a>
+  <a href="https://github.com/Ark0N/Codeman/commits/master"><img src="https://img.shields.io/github/commit-activity/t/Ark0N/Codeman?style=flat-square&color=1e3a5f" alt="Total commits"></a>
 </p>
 
 <p align="center">
@@ -21,7 +24,33 @@
 </p>
 
 <p align="center">
-  <img src="docs/images/subagent-demo.gif" alt="Codeman — parallel subagent visualization" width="900">
+  <img src="docs/images/subagent-demo-20260724.gif" alt="Codeman — parallel subagent visualization" width="900">
+</p>
+
+**Codeman** is a self-hosted mission control for AI coding agents. It spawns Claude Code, OpenCode, Codex, or Gemini CLI inside persistent tmux sessions, streams the real terminal to any browser, and keeps agents productive after you walk away: it re-prompts on idle, resumes when a usage limit resets, runs scheduled jobs, and shows every background agent working in real time.
+
+Get started in one line (macOS & Linux, Windows via WSL):
+
+```bash
+curl -fsSL https://getcodeman.com/install | bash
+```
+
+```bash
+codeman web
+# Open http://localhost:3000 and start your first session
+```
+
+The installer asks before every system change, and re-running the same line updates in place. Full details: [Quick Start - Installation](#quick-start---installation).
+
+- **One dashboard, four CLIs** - run [Claude Code, OpenCode, Codex, or Gemini](#more-features) per session (plus plain shell), locally, [in Docker](#isolated-docker-sessions), or [over SSH](#remote-ssh-sessions)
+- **Truly phone-friendly** - a [touch-optimized terminal](#mobile-optimized-web-ui) with instant local echo, QR login, swipe navigation, and push notifications
+- **Runs while you sleep** - [idle detection + respawn cycling](#respawn-controller) and auto-resume when a subscription limit resets, for 24+ hour unattended runs
+- **See your agents think** - [live floating windows](#live-agent-visualization) for every subagent and teammate, with real-time transcripts
+- **Nothing gets lost** - tmux persistence across restarts and network drops, exactly-once input delivery, full-scrollback replay
+- **Self-hosted and private** - loopback-only by default, MIT licensed, no telemetry, runs entirely on your machine
+
+<p align="center">
+  <img src="docs/images/codeman-tour-20260724.png" alt="Codeman dashboard tour: session tabs per case, one-click Run for new agents, live plan usage in the header" width="900">
 </p>
 
 ---
@@ -29,21 +58,37 @@
 ## Quick Start - Installation
 
 ```bash
-curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash
+curl -fsSL https://getcodeman.com/install | bash
 ```
 
-This installs Node.js and tmux if missing, clones Codeman to `~/.codeman/app`, and builds it.
+This installs Node.js and tmux if missing, clones Codeman to `~/.codeman/app`, and builds it. A few things worth knowing:
 
-You'll need at least one AI coding CLI installed — [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), or [Codex](https://developers.openai.com/codex/cli) (any combination works). After install:
+- **It asks first.** Every system change (package installs, AI CLI download) is prompted, and a menu at the end lets you choose: run Codeman in this terminal, install it as a background service (systemd/launchd, auto-start on boot), or don't start yet. Nothing runs in the background unless you pick it.
+- **Network or local-only, your choice.** The installer asks whether the dashboard should be reachable from other devices on your network (`0.0.0.0`, the default, with a strongly recommended password prompt) or from this machine only (`127.0.0.1`, safest). Skipping the password on a network bind requires an explicit confirmation and ends with a loud warning. A bare `codeman web` started by hand still defaults to loopback.
+- **Re-run to update.** The same one-liner updates a finished install in place: local changes in `~/.codeman/app` are stashed (never discarded), and a running service is restarted and verified. If a first install was interrupted, re-running resumes the full setup instead. `install.sh update` and `install.sh uninstall` also exist.
+- **CI / headless:** without a terminal attached, steps that would change your system abort with instructions instead of running silently. Set `CODEMAN_NONINTERACTIVE=1` to approve them for automation.
+
+You'll need at least one AI coding CLI installed — [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), [Codex](https://developers.openai.com/codex/cli), or [Gemini CLI](https://github.com/google-gemini/gemini-cli) (any combination works). The installer detects whichever of the four is present; if none is found, it offers to install Claude Code or OpenCode, or you can skip and install one yourself later. After install:
 
 ```bash
 codeman web
 # Open http://localhost:3000 and start your first session
 ```
 
+**Sharing with a small team?** Start it in multi-user mode instead: each person gets their own login and workspace.
+
+```bash
+codeman users add alice --admin      # create the first admin account
+codeman web --multiuser              # named logins + per-user case spaces
+```
+
+Details in [Multi-User Mode](#multi-user-mode-opt-in) below.
+
 <details>
 <summary><strong>Run as a background service</strong></summary>
 
+The installer's final menu sets this up for you (option 2) and verifies the service actually comes up before claiming success. To configure it manually instead:
+
 **Linux (systemd):**
 
 ```bash
@@ -103,15 +148,67 @@ launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.codeman.web.plist
 <summary><strong>Windows (WSL)</strong></summary>
 
 ```powershell
-wsl bash -c "curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash"
+wsl bash -c "curl -fsSL https://getcodeman.com/install | bash"
 ```
 
-Codeman requires tmux, so Windows users need [WSL](https://learn.microsoft.com/en-us/windows/wsl/install). If you don't have WSL yet: run `wsl --install` in an admin PowerShell, reboot, open Ubuntu, then install your preferred AI coding CLI inside WSL ([Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), or [Codex](https://developers.openai.com/codex/cli)). After installing, `http://localhost:3000` is accessible from your Windows browser.
+Codeman requires tmux, so Windows users need [WSL](https://learn.microsoft.com/en-us/windows/wsl/install). If you don't have WSL yet: run `wsl --install` in an admin PowerShell, reboot, open Ubuntu, then install your preferred AI coding CLI inside WSL ([Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), [Codex](https://developers.openai.com/codex/cli), or [Gemini CLI](https://github.com/google-gemini/gemini-cli)). After installing, `http://localhost:3000` is accessible from your Windows browser.
 
 </details>
 
 ---
 
+## Mobile-Optimized Web UI
+
+The most responsive AI coding agent experience on any phone. Full xterm.js terminal with local echo, swipe navigation, and a touch-optimized interface designed for real remote work — not a desktop UI crammed onto a small screen.
+
+<table>
+<tr>
+<td align="center" width="40%"><img src="docs/screenshots/mobile-session-keyboard-20260727.png" alt="Mobile — answering an agent's plan prompt with the keyboard accessory bar and Enter button" width="300"></td>
+<td align="center" width="60%"><img src="docs/screenshots/mobile-toolbar-enter-20260727.png" alt="Mobile toolbar: accessory bar with /init, /clear, clipboard and Esc above the Run, case, stop, Enter, voice and settings controls" width="440"></td>
+</tr>
+<tr>
+<td align="center"><em>Answering prompts by touch</em></td>
+<td align="center"><em>Accessory bar + dedicated Enter button</em></td>
+</tr>
+</table>
+
+<table>
+<tr>
+<th>Terminal Apps</th>
+<th>Codeman Mobile</th>
+</tr>
+<tr><td>200-300ms input lag over remote</td><td><b>Local echo — instant feedback</b></td></tr>
+<tr><td>Tiny text, no context</td><td>Full xterm.js terminal</td></tr>
+<tr><td>No session management</td><td>Swipe between sessions</td></tr>
+<tr><td>No notifications</td><td>Push alerts for approvals and idle</td></tr>
+<tr><td>Manual reconnect</td><td>tmux persistence</td></tr>
+<tr><td>No agent visibility</td><td>Background agents in real-time</td></tr>
+<tr><td>Copy-paste slash commands</td><td>One-tap <code>/init</code>, <code>/clear</code>, <code>/compact</code></td></tr>
+<tr><td>Password typing on phone</td><td><b>QR code scan — instant auth</b></td></tr>
+</table>
+
+- **Keyboard accessory bar** — `/init`, `/clear`, `/compact` quick-action buttons above the virtual keyboard; destructive commands require a double-press to confirm, so you never fire one by accident
+- **Dedicated Enter button** — replays the keypress through the terminal, so text buffered by local echo is flushed first rather than stranded
+- **Swipe navigation & smart keyboard handling** — swipe left/right to switch sessions; toolbar and terminal shift up when the keyboard opens (`visualViewport` API)
+- **Built for phones** — safe-area insets for notch and home indicator, 44px touch targets, bottom-sheet case picker, native momentum scrolling
+
+```bash
+codeman web --https
+# Open on your phone: https://<your-ip>:3000
+```
+
+> `localhost` works over plain HTTP. Use `--https` when accessing from another device, or use [Tailscale](https://tailscale.com/) (recommended): the installer can set it up for you (choose **Tailscale** at the network-access prompt, or run `bash ~/.codeman/app/install.sh tailscale` on an existing install). That gives you `https://<your-machine>.<tailnet>.ts.net` with a real certificate: private to your tailnet, no password required, and PWA install + push notifications work on your phone.
+
+### Secure QR Code Authentication
+
+Typing passwords on a phone keyboard is miserable. Codeman replaces it with **cryptographically secure single-use QR tokens** — scan the code displayed on your desktop and your phone is authenticated instantly.
+
+Each QR encodes a URL containing a 6-character short code that maps to a 256-bit secret (`crypto.randomBytes(32)`) on the server. Tokens auto-rotate every **60 seconds**, are **atomically consumed on first scan** (replays always fail), and use **hash-based `Map.get()` lookup** that leaks nothing through response timing. The short code is an opaque pointer — the real secret never appears in browser history, `Referer` headers, or Cloudflare edge logs.
+
+The security design addresses all 6 critical QR auth flaws identified in ["Demystifying the (In)Security of QR Code-based Login"](https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-xin) (USENIX Security 2025, which found 47 of the top-100 websites vulnerable): single-use enforcement, short TTL, cryptographic randomness, server-side generation, real-time desktop notification on scan (QRLjacking detection), and IP + User-Agent session binding with manual revocation. Dual-layer rate limiting (per-IP + global) makes brute force infeasible across 62^6 = 56.8 billion possible codes. Full security analysis: [`docs/qr-auth-plan.md`](docs/qr-auth-plan.md)
+
+---
+
 ## Using Codeman — A Human's Guide
 
 A start-to-finish walkthrough for driving Codeman from the browser. If you just installed, this is where to begin.
@@ -142,9 +239,9 @@ Hit start — Codeman spawns the CLI via a real PTY and streams it to your brows
 
 ### 3. Read the dashboard
 
-- **Tabs (top)** — one per session. `Alt+1`-`9` to jump, `Ctrl+Tab` for next, drag to reorder.
+- **Tabs (top)** — one per session. `Alt+1`-`9` to jump, `Ctrl+Tab` for next, drag to reorder (tab order syncs across your devices).
 - **Terminal (center)** — a real `xterm.js` terminal; full TUIs render correctly. Type directly and press **Enter** to send. `Shift+Enter` inserts a newline.
-- **Side panels** — Respawn, Ralph, Orchestrator, Cron, Subagents, Settings (toggled from the toolbar).
+- **Side panels** — Respawn, Orchestrator, Cron, Subagents, Settings (toggled from the toolbar).
 
 ### 4. Talk to the agent
 
@@ -155,13 +252,12 @@ Hit start — Codeman spawns the CLI via a real PTY and streams it to your brows
 
 ### 5. Make it autonomous
 
-| Mode             | Use it for                                                                                                                        | Where              |
-| ---------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------ |
-| **Respawn**      | Long unattended runs — auto-restarts the CLI on idle/limit, with adaptive timing. Presets: `solo-work`, `overnight-autonomous`, … | Respawn tab        |
-| **Ralph / Todo** | A self-driving loop that tracks a todo list and keeps working until done.                                                         | Ralph tab          |
-| **Orchestrator** | Turn one goal into a phased plan and drive it to completion across agents.                                                        | Orchestrator panel |
-| **Cron**         | Saved, named jobs on a schedule (`once`/`interval`/`daily`/`weekly`) that spawn a session and send a prompt when due.             | ⏰ Cron button     |
-| **Auto-resume**  | Automatically continue after a subscription rate-limit resets.                                                                    | Respawn tab (top)  |
+| Mode             | Use it for                                                                                                                        | Where                                                               |
+| ---------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
+| **Respawn**      | Long unattended runs — auto-restarts the CLI on idle/limit, with adaptive timing. Presets: `solo-work`, `overnight-autonomous`, … | Respawn tab                                                         |
+| **Orchestrator** | Turn one goal into a phased plan and drive it to completion across agents.                                                        | Orchestrator panel                                                  |
+| **Cron**         | Saved, named jobs on a schedule (`once`/`interval`/`daily`/`weekly`) that spawn a session and send a prompt when due.             | ⏰ Cron button _(opt-in: App Settings → Display → Header Displays)_ |
+| **Auto-resume**  | Automatically continue after a subscription rate-limit resets.                                                                    | Respawn tab (top)                                                   |
 
 ### 6. Reach it from anywhere
 
@@ -171,7 +267,7 @@ Hit start — Codeman spawns the CLI via a real PTY and streams it to your brows
 
 ### 7. Operate & maintain
 
-- **App Settings** — model, effort, theme/skin, notifications, display toggles, per-CLI options.
+- **App Settings** — model, effort, permission startup mode, theme/skin, notifications, display toggles, per-CLI options, a synced custom display name, and per-device English/Simplified Chinese UI language.
 - **Self-update** — git-clone installs update in place from **Settings → Updates**.
 - **Deploy your own changes** — see [Development](#development).
 
@@ -179,87 +275,10 @@ Hit start — Codeman spawns the CLI via a real PTY and streams it to your brows
 
 ---
 
-## Mobile-Optimized Web UI
-
-The most responsive AI coding agent experience on any phone. Full xterm.js terminal with local echo, swipe navigation, and a touch-optimized interface designed for real remote work — not a desktop UI crammed onto a small screen.
-
-<table>
-<tr>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-landing-qr.png" alt="Mobile — landing page with QR auth" width="260"></td>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-session-idle.png" alt="Mobile — idle session with keyboard accessory" width="260"></td>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-session-active.png" alt="Mobile — active agent session" width="260"></td>
-</tr>
-<tr>
-<td align="center"><em>Landing page with QR auth</em></td>
-<td align="center"><em>Keyboard accessory bar</em></td>
-<td align="center"><em>Agent working in real-time</em></td>
-</tr>
-</table>
-
-<table>
-<tr>
-<th>Terminal Apps</th>
-<th>Codeman Mobile</th>
-</tr>
-<tr><td>200-300ms input lag over remote</td><td><b>Local echo — instant feedback</b></td></tr>
-<tr><td>Tiny text, no context</td><td>Full xterm.js terminal</td></tr>
-<tr><td>No session management</td><td>Swipe between sessions</td></tr>
-<tr><td>No notifications</td><td>Push alerts for approvals and idle</td></tr>
-<tr><td>Manual reconnect</td><td>tmux persistence</td></tr>
-<tr><td>No agent visibility</td><td>Background agents in real-time</td></tr>
-<tr><td>Copy-paste slash commands</td><td>One-tap <code>/init</code>, <code>/clear</code>, <code>/compact</code></td></tr>
-<tr><td>Password typing on phone</td><td><b>QR code scan — instant auth</b></td></tr>
-</table>
-
-### Secure QR Code Authentication
-
-Typing passwords on a phone keyboard is miserable. Codeman replaces it with **cryptographically secure single-use QR tokens** — scan the code displayed on your desktop and your phone is authenticated instantly.
-
-Each QR encodes a URL containing a 6-character short code that maps to a 256-bit secret (`crypto.randomBytes(32)`) on the server. Tokens auto-rotate every **60 seconds**, are **atomically consumed on first scan** (replays always fail), and use **hash-based `Map.get()` lookup** that leaks nothing through response timing. The short code is an opaque pointer — the real secret never appears in browser history, `Referer` headers, or Cloudflare edge logs.
-
-The security design addresses all 6 critical QR auth flaws identified in ["Demystifying the (In)Security of QR Code-based Login"](https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-xin) (USENIX Security 2025, which found 47 of the top-100 websites vulnerable): single-use enforcement, short TTL, cryptographic randomness, server-side generation, real-time desktop notification on scan (QRLjacking detection), and IP + User-Agent session binding with manual revocation. Dual-layer rate limiting (per-IP + global) makes brute force infeasible across 62^6 = 56.8 billion possible codes. Full security analysis: [`docs/qr-auth-plan.md`](docs/qr-auth-plan.md)
-
-### Touch-Optimized Interface
-
-- **Keyboard accessory bar** — `/init`, `/clear`, `/compact` quick-action buttons above the virtual keyboard. Destructive commands (`/clear`, `/compact`) require a double-press to confirm — first tap arms the button, second tap executes — so you never fire one by accident on a bumpy commute
-- **Swipe navigation** — left/right on the terminal to switch sessions (80px threshold, 300ms)
-- **Smart keyboard handling** — toolbar and terminal shift up when keyboard opens (uses `visualViewport` API with 100px threshold for iOS address bar drift)
-- **Safe area support** — respects iPhone notch and home indicator via `env(safe-area-inset-*)`
-- **44px touch targets** — all buttons meet iOS Human Interface Guidelines minimum sizes
-- **Bottom sheet case picker** — slide-up modal replaces the desktop dropdown
-- **Native momentum scrolling** — `-webkit-overflow-scrolling: touch` for buttery scroll
-
-```bash
-codeman web --https
-# Open on your phone: https://<your-ip>:3000
-```
-
-> `localhost` works over plain HTTP. Use `--https` when accessing from another device, or use [Tailscale](https://tailscale.com/) (recommended) — it provides a private network so you can access `http://<tailscale-ip>:3000` from your phone without TLS certificates.
-
----
-
-## Live Agent Visualization
-
-Watch background agents work in real-time. Codeman monitors agent activity and displays each agent in a draggable floating window with animated Matrix-style connection lines back to the parent session.
-
-<p align="center">
-  <img src="docs/images/subagent-spawn.png" alt="Subagent Visualization" width="900">
-</p>
-
-- **Floating terminal windows** — draggable, resizable panels for each agent with a live activity log showing every tool call, file read, and progress update as it happens
-- **Connection lines** — animated green lines linking parent sessions to their child agents, updating in real-time as agents spawn and complete
-- **Status & model badges** — green (active), yellow (idle), blue (completed) indicators with Haiku/Sonnet/Opus model color coding
-- **Auto-behavior** — windows auto-open on spawn, auto-minimize on completion, tab badge shows "AGENT" or "AGENTS (n)" count
-- **Nested agents** — supports 3-level hierarchies (lead session -> teammate agents -> sub-subagents)
-
-**Agent Teams** — first-class support for Claude Code's native multi-agent teams (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`). `TeamWatcher` polls `~/.claude/teams/`, matches teammates to their lead session, and surfaces them as live subagent windows with **team-aware idle detection** — so the Respawn Controller won't fire while teammates are still working. See [`docs/agent-teams/`](docs/agent-teams/).
-
----
-
 ## Zero-Lag Input Overlay
 
 <p align="center">
-  <img src="docs/images/zerolag-demo.gif" alt="Zerolag Demo — local echo vs server echo side-by-side" width="900">
+  <img src="docs/images/zerolag-demo-20260728.gif" alt="Zerolag demo: instant local echo next to 600ms-2.7s server echo, side by side on two phones" width="900">
 </p>
 
 When accessing your coding agent remotely (VPN, Tailscale, SSH tunnel), every keystroke normally takes 200-300ms to round-trip. Codeman implements a **Mosh-inspired local echo system** that makes typing feel instant regardless of latency.
@@ -276,6 +295,30 @@ A pixel-perfect DOM overlay inside xterm.js renders keystrokes at 0ms. Backgroun
 
 ---
 
+## Live Agent Visualization
+
+Watch background agents work in real-time. Codeman monitors agent activity and displays each agent in a draggable floating window with animated Matrix-style connection lines back to the parent session.
+
+<p align="center">
+  <img src="docs/images/subagent-windows-20260724.png" alt="Subagent Visualization: three parallel Explore agents as floating windows with live tool-call feeds" width="900">
+</p>
+
+- **Floating terminal windows** — draggable, resizable panels for each agent with a live activity log showing every tool call, file read, and progress update as it happens
+- **Connection lines** — animated green lines linking parent sessions to their child agents, updating in real-time as agents spawn and complete
+- **Status & model badges** — green (active), yellow (idle), blue (completed) indicators with Haiku/Sonnet/Opus model color coding
+- **Auto-behavior** — windows auto-open on spawn, auto-minimize on completion, tab badge shows "AGENT" or "AGENTS (n)" count
+- **Nested agents** — supports 3-level hierarchies (lead session -> teammate agents -> sub-subagents)
+
+Multi-agent Workflow runs ("ultracode") get the same treatment: a floating run window tracks the whole workflow live, with phases, per-agent token counts, and the current tool of every agent:
+
+<p align="center">
+  <img src="docs/images/ultracode-window-20260724.png" alt="Ultracode workflow visualization: a live run window with per-agent tokens and phases" width="900">
+</p>
+
+**Agent Teams** — first-class support for Claude Code's native multi-agent teams (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`). `TeamWatcher` polls `~/.claude/teams/`, matches teammates to their lead session, and surfaces them as live subagent windows with **team-aware idle detection** — so the Respawn Controller won't fire while teammates are still working. See [`docs/agent-teams/`](docs/agent-teams/).
+
+---
+
 ## Respawn Controller
 
 The core of autonomous work. When the agent goes idle, the Respawn Controller detects it, sends a continue prompt, cycles context management commands for fresh context, and resumes — running **24+ hours** completely unattended.
@@ -302,7 +345,7 @@ Beyond single-session respawn, the **Orchestrator** turns a high-level goal into
 - **Crash-safe** — full state persists under the `orchestrator` key in `state.json`, so it survives restarts
 - **Driven from the UI or API** — the Orchestrator panel, or `POST /api/orchestrator/start` → `/approve` → `/status` (10 endpoints)
 
-> Distinct from Ralph (a single-session autonomous loop): the orchestrator coordinates multi-phase, multi-agent execution. Full design: [`docs/orchestrator-loop-architecture.md`](docs/orchestrator-loop-architecture.md).
+> Full design: [`docs/orchestrator-loop-architecture.md`](docs/orchestrator-loop-architecture.md).
 
 ---
 
@@ -310,14 +353,18 @@ Beyond single-session respawn, the **Orchestrator** turns a high-level goal into
 
 Run **20 parallel sessions** with full visibility — real-time xterm.js terminals at 60fps, per-session token and cost tracking, tab-based navigation, and one-click management.
 
-<p align="center">
-  <img src="docs/screenshots/multi-session-dashboard.png" alt="Multi-Session Dashboard" width="800">
-</p>
-
 ### Persistent Sessions
 
 Every session runs inside **tmux** — sessions survive server restarts, network drops, and machine sleep. Auto-recovery on startup with dual redundancy. Ghost session discovery finds orphaned tmux sessions. Managed sessions are environment-tagged so the agent won't kill its own session.
 
+### Session Manager & Command Palette
+
+`Ctrl/Cmd/Alt+K` opens a fuzzy session palette; **Browse all sessions** opens the Session Manager: one deduped list of everything Codeman knows about (live sessions, past sessions from state and lifecycle history, and Claude transcripts), each row showing its first and most recent prompt.
+
+- **Pinning**: pin a session to float it to the top of the list. Pinned sessions even survive kill (they demote to a lightweight stopped entry that stays visible and resumable).
+- **Name retention**: resuming a past session keeps its original name instead of minting a new one.
+- **Cross-device tab order**: drag-reordered tabs persist server-side, so your ordering follows you from desktop to phone.
+
 ### Hostname-Aware Window Title
 
 Running Codeman on multiple hosts (laptop, dev box, NAS)? The browser tab title is `codeman:<hostname>` so you can tell which backend each tab points at without clicking in:
@@ -340,14 +387,6 @@ The title is templated into the served HTML on first byte, so it's correct from
 
 Real-time desktop alerts when sessions need attention — `permission_prompt` and `elicitation_dialog` trigger critical red tab blinks, `idle_prompt` triggers yellow blinks. Click any notification to jump directly to the affected session. Hooks auto-configured per case directory.
 
-### Ralph / Todo Tracking
-
-Auto-detects Ralph Loops, `<promise>` tags, TodoWrite progress (`4/9 complete`), and iteration counters (`[5/50]`) with real-time progress rings and elapsed time tracking.
-
-<p align="center">
-  <img src="docs/images/ralph-tracker-8tasks-44percent.png" alt="Ralph Loop Tracking" width="800">
-</p>
-
 ### Run Summary
 
 Click the chart icon on any session tab to see a timeline of everything that happened — respawn cycles, token milestones, auto-compact triggers, idle/working transitions, hook events, errors, and more.
@@ -365,17 +404,70 @@ PTY Output → 16ms Server Batch → DEC 2026 Wrap → SSE → Client rAF → xt
 ## More Features
 
 - **Self-update** — git-clone installs under systemd/launchd update in place from **App Settings → Updates**: it detects the latest release, auto-stashes a dirty tree, and streams build progress across the service restart (npm installs report as non-updatable)
-- **Multi-CLI** — run **Claude Code**, **OpenCode**, or **Codex** per session; env-var prefixes auto-gate (`CLAUDE_CODE_*` vs `OPENCODE_*` vs `CODEX_*`). See [`docs/opencode-integration.md`](docs/opencode-integration.md)
+- **Multi-CLI** — run **Claude Code**, **OpenCode**, **Codex**, or **Gemini** per session; env-var prefixes auto-gate (`CLAUDE_CODE_*` vs `OPENCODE_*` vs `CODEX_*` vs `GEMINI_*`/`GOOGLE_*`). See [`docs/opencode-integration.md`](docs/opencode-integration.md)
+- **Docker sessions** — run a case inside an isolated, hardened container. One checkbox on **Create New** spins up a container with sensible defaults and starts the agent inside it; multiple sessions share one per-case container; export a container + its workspace to a portable `.tar.gz` to move it to another machine. See [`docs/docker-cases.md`](docs/docker-cases.md)
+- **Remote SSH sessions** — point a case at another machine and run the agent there inside a durable remote tmux: survives SSH drops, auto-reconnects, and can discover + attach sessions already running on the host. See [`docs/remote-sessions.md`](docs/remote-sessions.md)
 - **Effort & Ultracode** — set a per-session default effort (`low`–`max`) or enable **ultracode** (dynamic multi-agent workflows). Soft defaults only — switchable anytime with `/effort` in-session. Extended-thinking budget is configurable too
 - **Voice input** — dictate prompts with Deepgram Nova-3 (Web Speech API fallback): toggle recording, auto-silence stop, live level meter (`Ctrl+Shift+V`)
 - **Image input** — paste or drag-and-drop images straight into a session
 - **Gesture control** _(opt-in)_ — a MediaPipe hand-tracking overlay to grab/drag session windows and pinch buttons, hands-free. Enable with `CODEMAN_GESTURE=1` + App Settings → Display
 - **Multi-monitor span** _(macOS)_ — one click opens a browser window maximized across all displays, so floating agent/gesture panels can cross the physical seam
+- **File Viewer button** _(opt-in)_ — a header button that toggles the built-in file browser panel with one tap; enable under App Settings → Display → Header Displays
 - **CJK / IME input** — full composition support for Chinese / Japanese / Korean
 - **OS notifications & hostname-aware titles** — desktop alerts and tab titles are prefixed `codeman:<host>` so multi-host setups stay unambiguous
 
 ---
 
+## Isolated Docker Sessions
+
+Run a case inside its own hardened Docker container instead of directly on your host — for security isolation, reproducible toolchains, and one-click portability.
+
+- **One click** — on **New Case → Create New**, tick **🐳 Run in an isolated Docker container**. Codeman creates the case folder, spins up a container with default settings, and starts the agent inside it. No host/image/network fields to fill in.
+- **Resource templates** — expand the checkbox for a **Small / Medium / Large / GPU** preset (memory, CPUs, GPU), or set your own. **Disk is elastic** — storage grows as data flows in, no fixed cap.
+- **Shared per-case container** — many sessions can `docker exec` into the same container; killing one session never tears the container out from under the others.
+- **Hardened by default** — non-root, `--cap-drop ALL`, `no-new-privileges`, PID/memory caps, never `--privileged` or the docker socket; a **sealed** profile (no host credentials, network off) is one toggle away.
+- **Seamless auth, isolated credentials** — your host Claude / Codex / Gemini / OpenCode logins work inside the container out of the box: credentials are seeded (copied) in at launch and onboarding/trust prompts are pre-answered, so no login wizard appears. The container keeps its own copies and never writes back to your host credential stores; only conversation transcripts are shared, and exports never capture secrets.
+- **Move it to another machine** — export a container's whole environment (toolchain + workspace) to a portable `.tar.gz`, `docker load` it on the other side, and import it into a fresh case.
+- **Durable** — reconnect after a restart lands back in the same live agent; a container stop/reboot resumes the conversation from the bind-mounted transcript.
+
+Prerequisite: just Docker (or Podman). The agent base image builds itself automatically on first use, with progress streamed to the UI (or pre-build it with `node scripts/build-agent-image.mjs`). Full guide: [`docs/docker-cases.md`](docs/docker-cases.md).
+
+---
+
+## Remote SSH Sessions
+
+Point a case at another machine and run the agent **there**, over SSH, with the same dashboard, mobile UI, and autonomy features. Your laptop is just a window onto a session that lives on the remote host.
+
+- **Durable by design**: the agent runs inside a dedicated tmux session on the remote host, so a dropped SSH connection, network change, or laptop sleep never kills the run. Reconnecting lands back in the same live conversation.
+- **Auto-reconnect**: a bounded-backoff watcher notices a dead SSH pane and silently reattaches to the still-running remote session (kill-switch in settings; intentional kills are never revived).
+- **Discover & attach**: list the `codeman-*` sessions already running on a host (started by that machine's own Codeman, or by another operator) and attach to one. Attached sessions you don't own **detach on tab close, never kill**.
+- **Shared sessions**: several clients can attach the same remote session at different window sizes without clamping each other; discovery shows a "shared" badge with the client count.
+- **Injection-safe**: every ssh command line flows through a single shell-escaping builder, and host/path/identity fields are schema-guarded.
+
+Set it up under **New Case → Remote** (host, user, identity file, optional jump host). Full design: [`docs/remote-sessions.md`](docs/remote-sessions.md).
+
+---
+
+## Multi-User Mode (opt-in)
+
+Share one Codeman with a small trusted team, each person getting their own login and workspace. **Off by default** — without the flag, nothing changes.
+
+Enable with `codeman web --multiuser` (or `CODEMAN_MULTIUSER=1`). Create the first admin, then manage users from the CLI or the **Users** tab in App Settings:
+
+```bash
+codeman users add alice --admin      # prompts for a password (or --password-stdin)
+codeman users add bob                # a regular user
+codeman users list
+```
+
+- **Per-user spaces** — each user's cases live under `~/codeman-users/<name>/cases`; sessions, cases, search, and real-time events are scoped to their owner. Admins see everything.
+- **Individually revocable logins** — named users with scrypt-hashed passwords in `~/.codeman/users.json`; disable, reset (one-time password), or delete an account at any time. Admin actions are audited to `~/.codeman/admin-audit.jsonl`.
+- **Safer defaults for regular users** — non-admins run Claude in `--permission-mode auto` (Anthropic's classifier-guarded mode); raw shell sessions, cron `launchCommand`, and skip-permissions require an explicit per-user grant.
+
+> ⚠️ **This separates workspaces; it does not sandbox users from each other.** Every session runs as the same OS account, so a determined user's agent can still reach another user's files. For real isolation, pair users with **Docker cases** or run separate instances under separate OS accounts. See [`docs/multi-user-plan.md`](docs/multi-user-plan.md) and the multi-user section of [`docs/security-architecture.md`](docs/security-architecture.md).
+
+---
+
 ## Remote Access — Cloudflare Tunnel
 
 Access Codeman from your phone or any device outside your local network using a free [Cloudflare quick tunnel](https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/do-more-with-tunnels/trycloudflare/) — no port forwarding, no DNS, no static IP required.
@@ -499,13 +591,14 @@ When someone authenticates via QR, the desktop shows a notification toast with t
 
 ## Security
 
-Codeman launches sessions with `--dangerously-skip-permissions`, so the web UI is by design a remote-code-execution surface for whoever can reach it — the whole security model exists to control _who_ that is. Recent hardening (v0.9.0 + v0.9.5) closes the browser-driven attack paths that bite self-hosted dev tools. Full model: [`docs/security-architecture.md`](docs/security-architecture.md). **Found a vulnerability?** See [`SECURITY.md`](SECURITY.md) for private disclosure and the list of known limitations.
+By default Codeman launches sessions with `--dangerously-skip-permissions`, so the web UI is by design a remote-code-execution surface for whoever can reach it — the whole security model exists to control _who_ that is. (The startup permission mode is configurable; see below.) Recent hardening (v0.9.0 + v0.9.5) closes the browser-driven attack paths that bite self-hosted dev tools. Full model: [`docs/security-architecture.md`](docs/security-architecture.md). **Found a vulnerability?** See [`SECURITY.md`](.github/SECURITY.md) for private disclosure and the list of known limitations.
 
 ### Network & access
 
-- **Loopback by default** — binds `127.0.0.1`, reachable only from the same machine, so the no-password default is safe out of the box. Binding a non-loopback host without `CODEMAN_PASSWORD` _starts but prints a loud warning_ with three concrete fixes (set a password, loopback + an authenticated tunnel, or explicitly acknowledge with `--allow-unauthenticated-network`)
+- **Loopback by default** — the server binary binds `127.0.0.1`, reachable only from the same machine, so the no-password default is safe out of the box (the guided installer asks about network access and configures the binding + password for you). Binding a non-loopback host without `CODEMAN_PASSWORD` _starts but prints a loud warning_ with three concrete fixes (set a password, loopback + an authenticated tunnel, or explicitly acknowledge with `--allow-unauthenticated-network`)
 - **Optional auth, real sessions** — HTTP Basic via `CODEMAN_USERNAME` (default `admin`) / `CODEMAN_PASSWORD`. Success issues an opaque 256-bit `codeman_session` cookie (`randomBytes(32)`) — validated server-side, not client-signed, so it can't be forged offline (24h TTL, auto-extend, device-context audit log)
 - **Per-IP rate limiting** — 10 failed attempts → `429` with `Retry-After` (15-min decay). A valid cookie or correct password recovers _immediately_ even while an attacker hammers the same IP — important because all tunnel traffic shares one loopback IP. QR auth has its own separate limiter
+- **Configurable permission mode** - `--dangerously-skip-permissions` is only the default. **App Settings → Claude CLI → Startup Mode** can switch new sessions to Anthropic's classifier-guarded `auto` mode (low-prompt, needs Claude Code 2.1.207+), `normal` prompting, or an explicit allowed-tools list. In multi-user mode, non-granted users are forced to `auto`, and shell sessions / skip-permissions require an explicit per-user grant
 
 ### Always-on browser hardening (v0.9.5)
 
@@ -519,7 +612,7 @@ These run for **every** request — before auth, even on the default no-password
 
 ### Input, files & headers
 
-- **Schema-validated inputs** — every API body is checked with Zod v4 schemas; a `CLAUDE_CODE_*` / `OPENCODE_*` / `CODEX_*` env-prefix allowlist gates which settings each CLI can receive
+- **Schema-validated inputs** — every API body is checked with Zod v4 schemas; a `CLAUDE_CODE_*` / `OPENCODE_*` / `CODEX_*` / `GEMINI_*` / `GOOGLE_*` env-prefix allowlist gates which settings each CLI can receive
 - **Path containment** — file routes `realpath` before boundary checks (no TOCTOU); `..`, absolute paths, and symlinks resolving outside the working dir are rejected. Caps: 10 MB text preview / 50 MB raw & download; `/api/download` blocklists sensitive paths (`.env`, `*credentials*`, `~/.ssh/`, `.aws/credentials`). SVG/HTML is served `octet-stream` + `nosniff` + attachment so it downloads rather than executes
 - **Security headers** — `Content-Security-Policy` (`default-src 'self'`, every exception enumerated), `X-Content-Type-Options: nosniff`, `X-Frame-Options: SAMEORIGIN`, HSTS over HTTPS, and CORS reflected **only** for `localhost` / `127.0.0.1` / `::1`
 
@@ -641,7 +734,6 @@ codeman session start -d /path/to/repo   # (s)  start a session
 codeman session list                     #      list sessions
 codeman session logs <id>                #      tail output
 codeman task add "fix the failing test"  # (t)  queue a task
-codeman ralph start --min-hours 8        # (r)  launch the autonomous loop
 codeman attach <path>                     #      attach a Claude hook context
 ```
 
@@ -655,7 +747,7 @@ Codeman registers Claude Code hooks that `POST /api/hook-event` (`permission_pro
 
 ## API
 
-REST over Fastify — **~160 handlers across 18 route modules**, plus an SSE stream and a WebSocket terminal channel. All responses use the `ApiResponse<T>` envelope (`{success, data}` / `{success, error, errorCode}`); `/api/v1/*` is a stable alias. A representative subset:
+REST over Fastify — **~190 handlers across 20 route modules**, plus an SSE stream and a WebSocket terminal channel. All responses use the `ApiResponse<T>` envelope (`{success, data}` / `{success, error, errorCode}`); `/api/v1/*` is a stable alias. A representative subset:
 
 ### Sessions
 
@@ -665,6 +757,9 @@ REST over Fastify — **~160 handlers across 18 route modules**, plus an SSE str
 | `POST`   | `/api/quick-start`         | Create case + start session (`{caseName?, mode?, effort?, envOverrides?}`)         |
 | `POST`   | `/api/sessions/:id/input`  | Send input (`{input, useMux?, clientId?, seq?}` — `clientId`+`seq` = exactly-once) |
 | `GET`    | `/api/sessions/:id/output` | Read terminal output                                                               |
+| `GET`    | `/api/sessions/unified`    | Unified live + history list (Session Manager) — `?q=&limit=`                       |
+| `POST`   | `/api/sessions/:id/pin`    | Pin/unpin in the Session Manager (`{pinned}`)                                      |
+| `PUT`    | `/api/session-order`       | Sync tab order across devices (`{order: [ids]}`)                                   |
 | `DELETE` | `/api/sessions/:id`        | Delete session                                                                     |
 
 ### Respawn
@@ -675,13 +770,6 @@ REST over Fastify — **~160 handlers across 18 route modules**, plus an SSE str
 | `POST` | `/api/sessions/:id/respawn/stop`   | Stop controller            |
 | `PUT`  | `/api/sessions/:id/respawn/config` | Update config              |
 
-### Ralph / Todo
-
-| Method | Endpoint                         | Description            |
-| ------ | -------------------------------- | ---------------------- |
-| `GET`  | `/api/sessions/:id/ralph-state`  | Get loop state + todos |
-| `POST` | `/api/sessions/:id/ralph-config` | Configure tracking     |
-
 ### Orchestrator
 
 | Method | Endpoint                    | Description                     |
@@ -744,7 +832,6 @@ flowchart TB
         end
 
         subgraph Detection["Detection Layer"]
-            RT["Ralph Tracker"]
             SW["Subagent Watcher<br/><small>~/.claude/projects/*/subagents</small>"]
             TW["Team Watcher<br/><small>~/.claude/teams/*</small>"]
         end
@@ -755,7 +842,7 @@ flowchart TB
         end
 
         subgraph External["External"]
-            CLI["AI CLI<br/><small>Claude Code / OpenCode / Codex</small>"]
+            CLI["AI CLI<br/><small>Claude Code / OpenCode / Codex / Gemini</small>"]
             BG["Background Agents<br/><small>(Task tool)</small>"]
         end
     end
@@ -768,7 +855,6 @@ flowchart TB
     SM --> RC
     SM --> ORC
     SM --> SS
-    S1 --> RT
     S1 --> SCR
     S2 --> SCR
     RC --> SCR
@@ -787,7 +873,7 @@ flowchart TB
 npm install
 npx tsx src/index.ts web    # Dev mode
 npm run build               # Production build
-npm test                    # Run tests
+npm run test:ci             # Run tests (the CI suite; browser suites need extra setup)
 ```
 
 See [CLAUDE.md](./CLAUDE.md) for full documentation.
@@ -817,7 +903,7 @@ Full details: [`docs/archive/code-structure-findings.md`](docs/archive/code-stru
 
 [![npm](https://img.shields.io/npm/v/xterm-zerolag-input?style=flat-square&color=22c55e)](https://www.npmjs.com/package/xterm-zerolag-input)
 
-Instant keystroke feedback overlay for xterm.js. Eliminates perceived input latency over high-RTT connections by rendering typed characters immediately as a pixel-perfect DOM overlay. Zero dependencies, configurable prompt detection, full state machine with 78 tests.
+Instant keystroke feedback overlay for xterm.js. Eliminates perceived input latency over high-RTT connections by rendering typed characters immediately as a pixel-perfect DOM overlay. Zero dependencies, 6.1 kB gzipped, configurable prompt detection, CJK/emoji wide-character support, full state machine with 175 tests.
 
 ```bash
 npm install xterm-zerolag-input
@@ -844,3 +930,8 @@ MIT — see [LICENSE](LICENSE)
 <p align="center">
   <strong>Track sessions. Visualize agents. Control respawn. Let it run while you sleep.</strong>
 </p>
+
+<p align="center">
+  If Codeman saves you time, <a href="https://github.com/Ark0N/Codeman/stargazers">a star</a> helps other people find it.<br>
+  Bug reports and feature ideas are welcome in <a href="https://github.com/Ark0N/Codeman/issues">Issues</a>.
+</p>

README.zh-CN.md

@@ -5,7 +5,7 @@
 <h2 align="center">AI 编程智能体的任务控制中心</h2>
 
 <p align="center">
-  <em>Claude Code &bull; OpenCode &bull; Codex —— 统一仪表盘 &bull; 任意设备</em>
+  <em>Claude Code &bull; OpenCode &bull; Codex &bull; Gemini &bull; 终端 —— 统一仪表盘 &bull; 任意设备</em>
 </p>
 
 <p align="center">
@@ -14,39 +14,73 @@
 
 <p align="center">
   <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-1e3a5f?style=flat-square" alt="License: MIT"></a>
-  <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/Node.js-18%2B-22c55e?style=flat-square&logo=node.js&logoColor=white" alt="Node.js 18+"></a>
+  <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/Node.js-22%2B-22c55e?style=flat-square&logo=node.js&logoColor=white" alt="Node.js 22+"></a>
   <a href="https://www.typescriptlang.org/"><img src="https://img.shields.io/badge/TypeScript-5.9-3b82f6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript 5.9"></a>
   <a href="https://fastify.dev/"><img src="https://img.shields.io/badge/Fastify-5.x-1e3a5f?style=flat-square&logo=fastify&logoColor=white" alt="Fastify"></a>
-  <img src="https://img.shields.io/badge/Tests-2861%20total-22c55e?style=flat-square" alt="Tests">
+  <a href="https://github.com/Ark0N/Codeman/graphs/contributors"><img src="https://img.shields.io/github/contributors/Ark0N/Codeman?style=flat-square&color=3b82f6" alt="Contributors"></a>
+  <a href="https://github.com/Ark0N/Codeman/commits/master"><img src="https://img.shields.io/github/commit-activity/t/Ark0N/Codeman?style=flat-square&color=1e3a5f" alt="Total commits"></a>
 </p>
 
 <p align="center">
-  <img src="docs/images/subagent-demo.gif" alt="Codeman — 并行子智能体可视化" width="900">
+  <img src="docs/images/subagent-demo-20260724.gif" alt="Codeman — 并行子智能体可视化" width="900">
+</p>
+
+<p align="center">
+  <img src="docs/images/codeman-tour-20260724.png" alt="Codeman 仪表盘导览：按项目分组的会话标签页、一键 Run 启动新智能体、页头实时用量" width="900">
 </p>
 
 > 本文档由英文版 [`README.md`](README.md) 翻译而来。如有出入，以英文版为准。
 
----
-
-## 快速开始 — 安装
+一行命令即可安装（macOS 和 Linux，Windows 通过 WSL）：
 
 ```bash
-curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash
+curl -fsSL https://getcodeman.com/install | bash
 ```
 
-该脚本会在缺失时自动安装 Node.js 和 tmux，把 Codeman 克隆到 `~/.codeman/app` 并完成构建。
-
-你至少需要安装一个 AI 编程 CLI —— [Claude Code](https://docs.anthropic.com/en/docs/claude-code)、[OpenCode](https://opencode.ai) 或 [Codex](https://developers.openai.com/codex/cli)（任意组合均可）。安装完成后：
-
 ```bash
 codeman web
 # 打开 http://localhost:3000，开启你的第一个会话
 ```
 
+安装器在每次系统改动前都会先询问；重跑同一条命令即可原地更新。详见[快速开始 — 安装](#快速开始--安装)。
+
+---
+
+## 快速开始 — 安装
+
+```bash
+curl -fsSL https://getcodeman.com/install | bash
+```
+
+该脚本会在缺失时自动安装 Node.js 和 tmux，把 Codeman 克隆到 `~/.codeman/app` 并完成构建。几点须知：
+
+- **先询问，后改动。** 所有系统级改动（安装软件包、下载 AI CLI）都会先征求确认；结束时的菜单可选择：直接在本终端运行、安装为后台服务（systemd/launchd，开机自启），或暂不启动。不选就不会有任何后台进程。
+- **重跑即更新。** 再次运行同一条命令即可原地更新已完成的安装：`~/.codeman/app` 中的本地改动会被 stash（绝不丢弃），运行中的服务会自动重启并校验。若首次安装中途失败，重跑会继续完成完整的安装流程。也可以使用 `install.sh update` 与 `install.sh uninstall`。
+- **CI / 无终端环境：** 没有终端时，涉及系统改动的步骤会带着说明中止，而不是静默执行；在自动化场景设置 `CODEMAN_NONINTERACTIVE=1` 即可批准这些步骤。
+
+你至少需要安装一个 AI 编程 CLI —— [Claude Code](https://docs.anthropic.com/en/docs/claude-code)、[OpenCode](https://opencode.ai)、[Codex](https://developers.openai.com/codex/cli) 或 [Gemini CLI](https://github.com/google-gemini/gemini-cli)（任意组合均可）。安装器会自动检测这四个中已安装的任意一个；若一个都没有，会提供安装 Claude Code 或 OpenCode 的选项，也可以选择跳过、稍后自行安装。安装完成后：
+
+```bash
+codeman web
+# 打开 http://localhost:3000，开启你的第一个会话
+```
+
+**想和小团队共用一台？** 改用多用户模式启动：每人拥有自己的登录与工作空间。
+
+```bash
+codeman users add alice --admin      # 创建第一个管理员账号
+codeman web --multiuser              # 命名登录 + 按用户隔离的案例空间
+```
+
+详见下文[多用户模式](#多用户模式可选启用)。
+
 <details>
 <summary><strong>作为后台服务运行</strong></summary>
 
+安装器结尾的菜单（选项 2）可以帮你完成这一步，并在宣告成功前校验服务确实已启动。如需手动配置：
+
 **Linux（systemd）：**
+
 ```bash
 mkdir -p ~/.config/systemd/user
 cat > ~/.config/systemd/user/codeman-web.service << EOF
@@ -69,6 +103,7 @@ loginctl enable-linger $USER
 ```
 
 **macOS（launchd）：**
+
 ```bash
 mkdir -p ~/Library/LaunchAgents
 cat > ~/Library/LaunchAgents/com.codeman.web.plist << EOF
@@ -96,16 +131,18 @@ cat > ~/Library/LaunchAgents/com.codeman.web.plist << EOF
 EOF
 launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.codeman.web.plist
 ```
+
 </details>
 
 <details>
 <summary><strong>Windows（WSL）</strong></summary>
 
 ```powershell
-wsl bash -c "curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash"
+wsl bash -c "curl -fsSL https://getcodeman.com/install | bash"
 ```
 
-Codeman 依赖 tmux，因此 Windows 用户需要 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install)。如果还没装 WSL：在管理员 PowerShell 中运行 `wsl --install`，重启，打开 Ubuntu，然后在 WSL 内安装你偏好的 AI 编程 CLI（[Claude Code](https://docs.anthropic.com/en/docs/claude-code)、[OpenCode](https://opencode.ai) 或 [Codex](https://developers.openai.com/codex/cli)）。安装完成后，即可从 Windows 浏览器访问 `http://localhost:3000`。
+Codeman 依赖 tmux，因此 Windows 用户需要 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install)。如果还没装 WSL：在管理员 PowerShell 中运行 `wsl --install`，重启，打开 Ubuntu，然后在 WSL 内安装你偏好的 AI 编程 CLI（[Claude Code](https://docs.anthropic.com/en/docs/claude-code)、[OpenCode](https://opencode.ai)、[Codex](https://developers.openai.com/codex/cli) 或 [Gemini CLI](https://github.com/google-gemini/gemini-cli)）。安装完成后，即可从 Windows 浏览器访问 `http://localhost:3000`。
+
 </details>
 
 ---
@@ -116,14 +153,12 @@ Codeman 依赖 tmux，因此 Windows 用户需要 [WSL](https://learn.microsoft.
 
 <table>
 <tr>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-landing-qr.png" alt="移动端 — 带二维码认证的登录页" width="260"></td>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-session-idle.png" alt="移动端 — 带键盘配件栏的空闲会话" width="260"></td>
-<td align="center" width="33%"><img src="docs/screenshots/mobile-session-active.png" alt="移动端 — 活动中的智能体会话" width="260"></td>
+<td align="center" width="40%"><img src="docs/screenshots/mobile-session-keyboard-20260727.png" alt="移动端 — 通过键盘配件栏与 Enter 按钮回答智能体的方案提示" width="300"></td>
+<td align="center" width="60%"><img src="docs/screenshots/mobile-toolbar-enter-20260727.png" alt="移动端工具栏：配件栏的 /init、/clear、剪贴板与 Esc，下方是 Run、案例、停止、Enter、语音与设置控件" width="440"></td>
 </tr>
 <tr>
-<td align="center"><em>带二维码认证的登录页</em></td>
-<td align="center"><em>键盘配件栏</em></td>
-<td align="center"><em>智能体实时工作中</em></td>
+<td align="center"><em>触控回答提示</em></td>
+<td align="center"><em>配件栏 + 独立 Enter 按钮</em></td>
 </tr>
 </table>
 
@@ -142,23 +177,10 @@ Codeman 依赖 tmux，因此 Windows 用户需要 [WSL](https://learn.microsoft.
 <tr><td>在手机上手打密码</td><td><b>扫二维码 —— 即时认证</b></td></tr>
 </table>
 
-### 安全的二维码认证
-
-在手机键盘上输密码太痛苦了。Codeman 用**密码学安全的一次性二维码令牌**取而代之 —— 扫描桌面上显示的二维码，手机即刻完成认证。
-
-每个二维码编码的是一个包含 6 字符短码的 URL，该短码在服务端映射到一个 256 位密钥（`crypto.randomBytes(32)`）。令牌每 **60 秒**自动轮换，**首次扫描即原子性消费**（重放永远失败），并采用**基于哈希的 `Map.get()` 查找**，不会通过响应时延泄露任何信息。短码只是一个不透明指针 —— 真正的密钥永远不会出现在浏览器历史、`Referer` 头或 Cloudflare 边缘日志中。
-
-该安全设计覆盖了 ["Demystifying the (In)Security of QR Code-based Login"](https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-xin)（USENIX Security 2025，该研究发现 Top-100 网站中有 47 个存在漏洞）所指出的全部 6 个关键二维码认证缺陷：强制一次性使用、短 TTL、密码学随机性、服务端生成、扫描时桌面实时通知（QRLjacking 检测），以及 IP + User-Agent 会话绑定与手动吊销。双层速率限制（按 IP + 全局）使得在 62^6 = 568 亿种可能短码空间内进行暴力破解变得不可行。完整安全分析见：[`docs/qr-auth-plan.md`](docs/qr-auth-plan.md)
-
-### 触控优化界面
-
-- **键盘配件栏** —— 在虚拟键盘上方提供 `/init`、`/clear`、`/compact` 快捷按钮。破坏性命令（`/clear`、`/compact`）需双击确认 —— 第一次点击「上膛」，第二次点击执行 —— 这样在颠簸的通勤路上也不会误触
-- **滑动导航** —— 在终端上左右滑动切换会话（阈值 80px，300ms）
-- **智能键盘处理** —— 键盘弹出时工具栏与终端整体上移（使用 `visualViewport` API，并对 iOS 地址栏漂移设置 100px 阈值）
-- **安全区适配** —— 通过 `env(safe-area-inset-*)` 适配 iPhone 刘海与底部 Home 指示条
-- **44px 触控目标** —— 所有按钮均满足 iOS 人机界面指南的最小尺寸
-- **底部抽屉式 case 选择器** —— 用上滑模态框替代桌面端下拉菜单
-- **原生惯性滚动** —— `-webkit-overflow-scrolling: touch`，丝滑流畅
+- **键盘配件栏** —— 在虚拟键盘上方提供 `/init`、`/clear`、`/compact` 快捷按钮；破坏性命令需双击确认，绝不误触
+- **独立的 Enter 按钮** —— 以按键方式回放，先冲刷本地回显缓冲的文本，不会让内容滞留在屏幕上
+- **滑动导航与智能键盘处理** —— 左右滑动切换会话；键盘弹出时工具栏与终端整体上移（`visualViewport` API）
+- **为手机而生** —— 刘海与 Home 指示条的安全区适配、44px 触控目标、底部抽屉式 case 选择器、原生惯性滚动
 
 ```bash
 codeman web --https
@@ -167,30 +189,86 @@ codeman web --https
 
 > `localhost` 走纯 HTTP 即可。从其他设备访问时请使用 `--https`，或使用 [Tailscale](https://tailscale.com/)（推荐）—— 它提供私有网络，让你无需 TLS 证书即可从手机访问 `http://<tailscale-ip>:3000`。
 
+### 安全的二维码认证
+
+在手机键盘上输密码太痛苦了。Codeman 用**密码学安全的一次性二维码令牌**取而代之 —— 扫描桌面上显示的二维码，手机即刻完成认证。
+
+每个二维码编码的是一个包含 6 字符短码的 URL，该短码在服务端映射到一个 256 位密钥（`crypto.randomBytes(32)`）。令牌每 **60 秒**自动轮换，**首次扫描即原子性消费**（重放永远失败），并采用**基于哈希的 `Map.get()` 查找**，不会通过响应时延泄露任何信息。短码只是一个不透明指针 —— 真正的密钥永远不会出现在浏览器历史、`Referer` 头或 Cloudflare 边缘日志中。
+
+该安全设计覆盖了 ["Demystifying the (In)Security of QR Code-based Login"](https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-xin)（USENIX Security 2025，该研究发现 Top-100 网站中有 47 个存在漏洞）所指出的全部 6 个关键二维码认证缺陷：强制一次性使用、短 TTL、密码学随机性、服务端生成、扫描时桌面实时通知（QRLjacking 检测），以及 IP + User-Agent 会话绑定与手动吊销。双层速率限制（按 IP + 全局）使得在 62^6 = 568 亿种可能短码空间内进行暴力破解变得不可行。完整安全分析见：[`docs/qr-auth-plan.md`](docs/qr-auth-plan.md)
+
 ---
 
-## 实时智能体可视化
+## 使用 Codeman —— 人类操作指南
 
-实时观看后台智能体工作。Codeman 监控智能体活动，将每个智能体显示在一个可拖拽的浮动窗口中，并用「黑客帝国」风格的动态连接线连回父会话。
+从头到尾走一遍如何在浏览器里驾驭 Codeman。如果你刚装好，就从这里开始。
 
-<p align="center">
-  <img src="docs/images/subagent-spawn.png" alt="子智能体可视化" width="900">
-</p>
+### 1. 启动服务器
 
-- **浮动终端窗口** —— 每个智能体一个可拖拽、可调整大小的面板，带实时活动日志，逐条展示每一次工具调用、文件读取与进度更新
-- **连接线** —— 用动态绿色线条连接父会话与其子智能体，随智能体的产生与完成实时更新
-- **状态与模型徽标** —— 绿色（活动）、黄色（空闲）、蓝色（已完成）指示，并以 Haiku/Sonnet/Opus 的颜色编码区分模型
-- **自动行为** —— 窗口在产生时自动打开、完成时自动最小化，标签徽标显示「AGENT」或「AGENTS (n)」计数
-- **嵌套智能体** —— 支持 3 层层级（主会话 → 团队成员智能体 → 子-子智能体）
+```bash
+codeman web                       # localhost:3000（仅环回 —— 安全默认值）
+codeman web --port 8080           # 自定义端口（或设置 CODEMAN_PORT）
+codeman web --https               # 自签名 TLS（仅远程访问时需要）
+codeman web -H 0.0.0.0            # 绑定局域网 —— 必须设置 CODEMAN_PASSWORD（见「安全」）
+```
 
-**智能体团队（Agent Teams）** —— 一等公民式支持 Claude Code 原生的多智能体团队（`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`）。`TeamWatcher` 轮询 `~/.claude/teams/`，将团队成员匹配到其主会话，并以实时子智能体窗口呈现，且具备**团队感知的空闲检测** —— 因此当团队成员仍在工作时，重生控制器不会被触发。详见 [`docs/agent-teams/`](docs/agent-teams/)。
+打开打印出的 URL。整个页面是一个单一仪表盘；下面的一切都在这里完成。
+
+### 2. 创建你的第一个会话
+
+点击 **+ New Session**（或 **Quick Start**）。一个会话就是一个运行在自己 tmux 终端里的 AI CLI。你可以选择：
+
+| 字段                   | 作用                                                                                        |
+| ---------------------- | ------------------------------------------------------------------------------------------- |
+| **工作目录 / case**    | 智能体操作的文件夹。「case」就是一个 Codeman 记住的命名工作目录。                           |
+| **CLI / 运行模式**     | `Claude`（默认）、`OpenCode`、`Codex`、`Gemini` 或 `Terminal`（普通 shell）。               |
+| **模型**               | 每会话模型（App Settings → Claude Model）。软默认值 —— 会话内 `/model` 依然有效。           |
+| **Effort / Ultracode** | 推理力度（`low`–`max`），或用 `ultracode` 开启动态多智能体工作流。随时可用 `/effort` 切换。 |
+
+点击启动 —— Codeman 通过真实 PTY 拉起 CLI，并经 SSE 流式传输到你的浏览器。
+
+### 3. 读懂仪表盘
+
+- **标签（顶部）** —— 每个会话一个。`Alt+1`–`9` 跳转，`Ctrl+Tab` 下一个，拖拽排序（标签顺序会跨设备同步）。
+- **终端（中央）** —— 真实的 `xterm.js` 终端；完整 TUI 正常渲染。直接输入并按 **Enter** 发送。`Shift+Enter` 插入换行。
+- **侧边面板** —— Respawn、Orchestrator、Cron、Subagents、Settings（从工具栏切换）。
+
+### 4. 与智能体对话
+
+- **直接在终端输入提示** —— 即使跨越重连，输入也是精确一次送达（连接中断绝不会丢失或重复发送提示）。
+- **粘贴或拖放图片**，直接进入会话。
+- **语音输入** —— `Ctrl+Shift+V`（Deepgram Nova-3，自动静音停止）。
+- **附件** —— 注册外部文件/文档，并内联预览 Office/PDF。
+
+### 5. 让它自主运行
+
+| 模式             | 用途                                                                                                      | 位置                                                               |
+| ---------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------ |
+| **Respawn**      | 长时间无人值守运行 —— 空闲/限额时自动重启 CLI，带自适应时序。预设：`solo-work`、`overnight-autonomous` 等 | Respawn 标签页                                                     |
+| **Orchestrator** | 把一个目标变成分阶段计划，并跨多个智能体推动完成。                                                        | 编排器面板                                                         |
+| **Cron**         | 已保存的、命名的定时任务（`once`/`interval`/`daily`/`weekly`），到期时拉起会话并发送提示。                | ⏰ Cron 按钮（可选启用：App Settings → Display → Header Displays） |
+| **Auto-resume**  | 订阅限额重置后自动继续。                                                                                  | Respawn 标签页（顶部）                                             |
+
+### 6. 随时随地访问
+
+- **手机/平板** —— UI 完全触控优化；扫描桌面上的**二维码**即可免密码登录。
+- **网络之外** —— `./scripts/tunnel.sh start` 打开一条 Cloudflare 隧道（先设置 `CODEMAN_PASSWORD`）。
+- **SSH** —— `sc` 选择器可从终端附着任意会话（`sc` 交互式，`sc 2` 快速附着，`sc -l` 列表）。
+
+### 7. 运维与维护
+
+- **App Settings** —— 模型、effort、权限启动模式、主题/皮肤、通知、显示开关、各 CLI 的专属选项，以及跨设备同步的自定义显示名称和按设备保存的英文/简体中文界面语言。
+- **自更新** —— git-clone 安装可在 **Settings → Updates** 中原地更新。
+- **部署你自己的改动** —— 见[开发](#开发)。
+
+> ⚠️ **安全提示：** 如果你正在 Codeman 受管会话*内部*工作（`echo $CODEMAN_MUX` → `1`），绝不要直接运行 `tmux kill-session` / `pkill claude` —— 请使用 Web UI 或 `./scripts/tmux-manager.sh`。
 
 ---
 
 ## 零延迟输入叠加层
 
 <p align="center">
-  <img src="docs/images/zerolag-demo.gif" alt="Zerolag 演示 —— 本地回显与服务端回显并排对比" width="900">
+  <img src="docs/images/zerolag-demo-20260728.gif" alt="Zerolag 演示：两台手机并排对比，即时本地回显与 600ms-2.7s 服务端回显" width="900">
 </p>
 
 远程访问你的编程智能体时（VPN、Tailscale、SSH 隧道），每次按键通常需要 200–300 毫秒往返。Codeman 实现了一套**受 Mosh 启发的本地回显系统**，无论延迟多高，打字都感觉即时。
@@ -207,6 +285,30 @@ xterm.js 内部一个像素级精准的 DOM 叠加层以 0ms 渲染按键。后
 
 ---
 
+## 实时智能体可视化
+
+实时观看后台智能体工作。Codeman 监控智能体活动，将每个智能体显示在一个可拖拽的浮动窗口中，并用「黑客帝国」风格的动态连接线连回父会话。
+
+<p align="center">
+  <img src="docs/images/subagent-windows-20260724.png" alt="子智能体可视化 —— 三个并行 Explore 智能体的浮动窗口与实时工具调用日志" width="900">
+</p>
+
+- **浮动终端窗口** —— 每个智能体一个可拖拽、可调整大小的面板，带实时活动日志，逐条展示每一次工具调用、文件读取与进度更新
+- **连接线** —— 用动态绿色线条连接父会话与其子智能体，随智能体的产生与完成实时更新
+- **状态与模型徽标** —— 绿色（活动）、黄色（空闲）、蓝色（已完成）指示，并以 Haiku/Sonnet/Opus 的颜色编码区分模型
+- **自动行为** —— 窗口在产生时自动打开、完成时自动最小化，标签徽标显示「AGENT」或「AGENTS (n)」计数
+- **嵌套智能体** —— 支持 3 层层级（主会话 → 团队成员智能体 → 子-子智能体）
+
+多智能体 Workflow 运行（「ultracode」）同样可视化：一个浮动运行窗口实时跟踪整个工作流，展示阶段、各智能体的 token 用量与当前工具：
+
+<p align="center">
+  <img src="docs/images/ultracode-window-20260724.png" alt="Ultracode 工作流可视化 —— 实时运行窗口，含各智能体 token 与阶段" width="900">
+</p>
+
+**智能体团队（Agent Teams）** —— 一等公民式支持 Claude Code 原生的多智能体团队（`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`）。`TeamWatcher` 轮询 `~/.claude/teams/`，将团队成员匹配到其主会话，并以实时子智能体窗口呈现，且具备**团队感知的空闲检测** —— 因此当团队成员仍在工作时，重生控制器不会被触发。详见 [`docs/agent-teams/`](docs/agent-teams/)。
+
+---
+
 ## 重生控制器（Respawn Controller）
 
 自主工作的核心。当智能体进入空闲，重生控制器会检测到，发送继续提示，循环执行上下文管理命令以获得全新上下文，然后恢复工作 —— 可完全无人值守运行 **24 小时以上**。
@@ -216,7 +318,7 @@ WATCHING → IDLE DETECTED → SEND UPDATE → /clear → /init → CONTINUE →
 ```
 
 - **多层空闲检测** —— 完成消息、AI 驱动的空闲检查、输出静默、token 稳定性
-- **用量限额自动恢复**（*可选，默认关闭*）—— 当 Claude 因订阅用量限额而停止（"You've hit your limit · resets 3pm"）时，Codeman 会解析重置时间，等到限额刷新（外加 2 分钟安全缓冲）后自动关闭限额对话框并发送 `continue`，让通宵任务平稳跨过 5 小时窗口而不是停摆到早晨。可识别 Claude Code 各版本的全部限额消息格式；若仍受限会自动重试；计划在 Codeman 重启后依然生效；暂停期间会阻止重生循环，避免 `/clear` 清掉等待中的对话。在会话 Respawn 标签页顶部按会话启用
+- **用量限额自动恢复**（_可选，默认关闭_）—— 当 Claude 因订阅用量限额而停止（"You've hit your limit · resets 3pm"）时，Codeman 会解析重置时间，等到限额刷新（外加 2 分钟安全缓冲）后自动关闭限额对话框并发送 `continue`，让通宵任务平稳跨过 5 小时窗口而不是停摆到早晨。可识别 Claude Code 各版本的全部限额消息格式；若仍受限会自动重试；计划在 Codeman 重启后依然生效；暂停期间会阻止重生循环，避免 `/clear` 清掉等待中的对话。在会话 Respawn 标签页顶部按会话启用
 - **熔断器** —— 当 Claude 卡住时防止重生抖动（CLOSED → HALF_OPEN → OPEN 状态，跟踪连续无进展与重复错误）
 - **健康评分** —— 0–100 健康分，分项涵盖循环成功率、熔断器状态、迭代进展与卡死恢复
 - **内置预设** —— `solo-work`（3s 空闲，60min）、`subagent-workflow`（45s，240min）、`team-lead`（90s，480min）、`ralph-todo`（8s，480min）、`overnight-autonomous`（10s，480min）
@@ -233,7 +335,7 @@ WATCHING → IDLE DETECTED → SEND UPDATE → /clear → /init → CONTINUE →
 - **崩溃安全** —— 完整状态持久化在 `state.json` 的 `orchestrator` 键下，可在重启后存续
 - **可从 UI 或 API 驱动** —— 编排器面板，或 `POST /api/orchestrator/start` → `/approve` → `/status`（共 10 个端点）
 
-> 与 Ralph（单会话自主循环）不同：编排器协调多阶段、多智能体执行。完整设计：[`docs/orchestrator-loop-architecture.md`](docs/orchestrator-loop-architecture.md)。
+> 完整设计：[`docs/orchestrator-loop-architecture.md`](docs/orchestrator-loop-architecture.md)。
 
 ---
 
@@ -241,14 +343,18 @@ WATCHING → IDLE DETECTED → SEND UPDATE → /clear → /init → CONTINUE →
 
 运行 **20 个并行会话**且全程可见 —— 60fps 的实时 xterm.js 终端、按会话的 token 与成本跟踪、基于标签的导航，以及一键管理。
 
-<p align="center">
-  <img src="docs/screenshots/multi-session-dashboard.png" alt="多会话仪表盘" width="800">
-</p>
-
 ### 持久化会话
 
 每个会话都运行在 **tmux** 内 —— 会话可在服务器重启、网络中断与机器休眠后存续。启动时自动恢复，具备双重冗余。幽灵会话发现机制能找到孤立的 tmux 会话。受管会话带有环境标签，因此智能体不会杀掉自己的会话。
 
+### 会话管理器与命令面板
+
+`Ctrl/Cmd/Alt+K` 打开模糊搜索的会话面板；**Browse all sessions** 打开会话管理器：一份去重后的完整清单，涵盖 Codeman 所知的一切（活动会话、来自状态与生命周期历史的既往会话，以及 Claude 转录），每一行都显示其第一条与最近一条提示。
+
+- **置顶（Pin）**：把会话固定到列表顶部。被置顶的会话甚至能挺过被杀掉（降级为一条轻量的已停止记录，依然可见、可恢复）。
+- **名称保留**：从会话管理器恢复既往会话时保留其原有名称，而不是生成一个新名称。
+- **跨设备标签顺序**：拖拽排序的标签顺序保存在服务端，你的排列会从桌面跟随到手机。
+
 ### 主机名感知的窗口标题
 
 在多台主机上运行 Codeman（笔记本、开发机、NAS）？浏览器标签标题是 `codeman:<主机名>`，让你无需点进去就能分辨每个标签对应哪个后端：
@@ -262,23 +368,15 @@ codeman web --title-hostname dev-box       # codeman:dev-box（用于覆盖嘈
 
 ### 智能 Token 管理
 
-| 阈值 | 动作 | 结果 |
-|-----------|--------|--------|
+| 阈值            | 动作            | 结果                   |
+| --------------- | --------------- | ---------------------- |
 | **110k tokens** | 自动 `/compact` | 上下文被摘要，工作继续 |
-| **140k tokens** | 自动 `/clear` | 以 `/init` 全新开始 |
+| **140k tokens** | 自动 `/clear`   | 以 `/init` 全新开始    |
 
 ### 通知
 
 当会话需要关注时实时桌面提醒 —— `permission_prompt` 与 `elicitation_dialog` 触发关键的红色标签闪烁，`idle_prompt` 触发黄色闪烁。点击任意通知即可直接跳转到相关会话。Hook 按 case 目录自动配置。
 
-### Ralph / Todo 跟踪
-
-自动检测 Ralph 循环、`<promise>` 标签、TodoWrite 进度（`4/9 complete`）以及迭代计数器（`[5/50]`），并提供实时进度环与已用时间跟踪。
-
-<p align="center">
-  <img src="docs/images/ralph-tracker-8tasks-44percent.png" alt="Ralph 循环跟踪" width="800">
-</p>
-
 ### 运行摘要（Run Summary）
 
 点击任意会话标签上的图表图标，即可看到所发生一切的时间线 —— 重生周期、token 里程碑、自动 compact 触发、空闲/工作切换、hook 事件、错误等等。
@@ -296,17 +394,70 @@ PTY 输出 → 16ms 服务端批处理 → DEC 2026 包裹 → SSE → 客户端
 ## 更多特性
 
 - **自更新** —— systemd/launchd 管理下的 git-clone 安装可在 **App Settings → Updates** 中原地更新：它会检测最新发行版，自动暂存（stash）脏工作树，并在服务重启期间流式展示构建进度（npm 安装会被报告为不可更新）
-- **多 CLI** —— 每个会话可选 **Claude Code**、**OpenCode** 或 **Codex**；环境变量前缀自动隔离（`CLAUDE_CODE_*`、`OPENCODE_*` 与 `CODEX_*`）。详见 [`docs/opencode-integration.md`](docs/opencode-integration.md)
+- **多 CLI** —— 每个会话可选 **Claude Code**、**OpenCode**、**Codex** 或 **Gemini**；环境变量前缀自动隔离（`CLAUDE_CODE_*`、`OPENCODE_*`、`CODEX_*` 与 `GEMINI_*`/`GOOGLE_*`）。详见 [`docs/opencode-integration.md`](docs/opencode-integration.md)
+- **Docker 会话** —— 在隔离且加固的容器中运行案例。**Create New** 上勾选一个复选框即可用合理的默认值启动容器并在其中启动智能体；同一案例的多个会话共享一个容器；可将容器连同工作区导出为可移植的 `.tar.gz`，迁移到另一台机器。详见 [`docs/docker-cases.md`](docs/docker-cases.md)
+- **远程 SSH 会话**：把案例指向另一台机器，让智能体在那里一个持久的远程 tmux 中运行：SSH 断连不中断任务、自动重连，还能发现并附着主机上已在运行的会话。详见 [`docs/remote-sessions.md`](docs/remote-sessions.md)
 - **Effort 与 Ultracode** —— 设置每会话的默认 effort（`low`–`max`），或启用 **ultracode**（动态多智能体工作流）。这些都只是软默认值 —— 会话中可随时用 `/effort` 切换。扩展思考预算也可配置
 - **语音输入** —— 用 Deepgram Nova-3 口述提示（带 Web Speech API 回退）：切换录音、自动静音停止、实时音量表（`Ctrl+Shift+V`）
 - **图像输入** —— 直接把图片粘贴或拖放进会话
-- **手势控制** *(可选)* —— 一个 MediaPipe 手部追踪叠加层，可徒手抓取/拖动会话窗口并捏合按钮。用 `CODEMAN_GESTURE=1` + App Settings → Display 启用
-- **多显示器横跨** *(macOS)* —— 一键打开一个横跨所有显示器最大化的浏览器窗口，让浮动的智能体/手势面板可以跨越物理拼接缝
+- **手势控制** _(可选)_ —— 一个 MediaPipe 手部追踪叠加层，可徒手抓取/拖动会话窗口并捏合按钮。用 `CODEMAN_GESTURE=1` + App Settings → Display 启用
+- **多显示器横跨** _(macOS)_ —— 一键打开一个横跨所有显示器最大化的浏览器窗口，让浮动的智能体/手势面板可以跨越物理拼接缝
+- **文件查看器按钮** _(可选)_ —— 头部新增一个按钮，一键切换内置文件浏览器面板；在 App Settings → Display → Header Displays 中启用
 - **CJK / 输入法支持** —— 完整支持中文 / 日文 / 韩文的组合输入
 - **操作系统通知与主机名感知标题** —— 桌面提醒与标签标题以 `codeman:<host>` 为前缀，使多主机配置不再含糊
 
 ---
 
+## 隔离的 Docker 会话
+
+让案例（case）运行在专属的加固 Docker 容器里，而不是直接跑在主机上：获得安全隔离、可复现的工具链和一键可移植性。
+
+- **一键启动** —— 在 **New Case → Create New** 中勾选 **🐳 Run in an isolated Docker container**。Codeman 会创建案例文件夹、用默认设置启动容器，并在容器内启动智能体。无需填写任何主机/镜像/网络字段。
+- **资源模板** —— 展开复选框可选 **Small / Medium / Large / GPU** 预设（内存、CPU、GPU），也可以完全自定义。**磁盘是弹性的** —— 存储随数据增长，没有固定上限。
+- **按案例共享容器** —— 多个会话可以 `docker exec` 进同一个容器；结束某个会话绝不会影响其他会话所在的容器。
+- **默认加固** —— 非 root、`--cap-drop ALL`、`no-new-privileges`、PID/内存上限，绝不使用 `--privileged` 或 docker socket；**密封（sealed）** 配置（不注入主机凭据、关闭网络）只需一个开关。
+- **无感认证、凭据隔离** —— 主机上的 Claude / Codex / Gemini / OpenCode 登录在容器内开箱即用：凭据在启动时以只读种子方式复制注入，onboarding/信任提示已预先答复，不会弹出登录向导。容器保留自己的副本，绝不回写主机的凭据存储；跨边界共享的只有对话转录，导出文件也绝不包含机密。
+- **迁移到另一台机器** —— 把容器的完整环境（工具链 + 工作区）导出为可移植的 `.tar.gz`，在另一台机器上导入到新案例即可继续。
+- **持久耐用** —— Codeman 重启后重连会回到同一个存活的智能体；容器停止/重启后则从绑定挂载的转录恢复对话。
+
+前置条件：只需 Docker（或 Podman）。智能体基础镜像会在首次使用时自动构建，构建进度实时显示在 UI 中（也可用 `node scripts/build-agent-image.mjs` 预构建）。完整指南：[`docs/docker-cases.md`](docs/docker-cases.md)。
+
+---
+
+## 远程 SSH 会话
+
+把案例（case）指向另一台机器，通过 SSH 让智能体**在那台机器上**运行，同时保留同样的仪表盘、移动端 UI 与自主运行特性。你的笔记本只是一扇窗口，会话本体活在远程主机上。
+
+- **天生持久**：智能体运行在远程主机上一个专用的 tmux 会话里，SSH 断连、网络切换或笔记本休眠都不会中断任务。重新连接后回到同一个活跃对话。
+- **自动重连**：一个带上限退避的监视器发现 SSH 面板断开后，会静默重新附着到仍在运行的远程会话（设置中有总开关；主动杀掉的会话绝不会被复活）。
+- **发现与附着**：列出主机上已在运行的 `codeman-*` 会话（由那台机器自己的 Codeman 或其他操作者启动）并附着其一。非你所有的已附着会话在关闭标签时**只分离，绝不杀掉**。
+- **共享会话**：多个客户端可以以不同窗口尺寸同时附着同一个远程会话而互不挤压；发现列表会显示带客户端计数的「shared」徽标。
+- **注入安全**：所有 ssh 命令行都经由单一的 shell 转义构建器生成，主机/路径/身份文件字段均有模式校验。
+
+在 **New Case → Remote** 中配置（主机、用户、身份文件、可选跳板机）。完整设计：[`docs/remote-sessions.md`](docs/remote-sessions.md)。
+
+---
+
+## 多用户模式（可选启用）
+
+与一个小型互信团队共享同一个 Codeman，每人拥有自己的登录与工作空间。**默认关闭**：不加该开关时，行为与单用户完全一致。
+
+用 `codeman web --multiuser`（或 `CODEMAN_MULTIUSER=1`）启用。创建第一个管理员后，可通过 CLI 或 App Settings 中的 **Users** 标签页管理用户：
+
+```bash
+codeman users add alice --admin      # 提示输入密码（或 --password-stdin）
+codeman users add bob                # 普通用户
+codeman users list
+```
+
+- **按用户的空间**：每个用户的案例位于 `~/codeman-users/<name>/cases`；会话、案例、搜索与实时事件都按属主隔离。管理员可以看到全部。
+- **可单独吊销的登录**：命名用户的密码以 scrypt 哈希保存在 `~/.codeman/users.json`；可随时禁用、重置（一次性密码）或删除账号。管理员操作审计记录在 `~/.codeman/admin-audit.jsonl`。
+- **普通用户的更安全默认值**：非管理员以 `--permission-mode auto` 运行 Claude（Anthropic 的分类器护栏模式）；raw shell 会话、cron `launchCommand` 与跳过权限模式需要按用户显式授权。
+
+> ⚠️ **这只是工作空间的划分，不是用户之间的沙箱。** 所有会话都以同一个操作系统账户运行，因此有心用户的智能体依然能触及他人的文件。若需要真正的隔离，请结合 **Docker 案例**，或在不同的操作系统账户下运行独立实例。参见 [`docs/multi-user-plan.md`](docs/multi-user-plan.md) 与 [`docs/security-architecture.md`](docs/security-architecture.md) 的多用户章节。
+
+---
+
 ## 远程访问 —— Cloudflare 隧道
 
 使用免费的 [Cloudflare 快速隧道](https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/do-more-with-tunnels/trycloudflare/)，从手机或本地网络外的任意设备访问 Codeman —— 无需端口转发、无需 DNS、无需静态 IP。
@@ -374,14 +525,14 @@ loginctl enable-linger $USER
 
 该设计参考了 ["Demystifying the (In)Security of QR Code-based Login"](https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-xin)（USENIX Security 2025），该研究发现 Top-100 网站中有 47 个因横跨 42 个 CVE 的 6 个关键设计缺陷而易受二维码认证攻击。Codeman 全部六个都做了应对：
 
-| USENIX 缺陷 | 缓解措施 |
-|-------------|------------|
-| **缺陷 1**：缺少一次性强制 | 令牌首次扫描即原子性消费 —— 重放永远失败 |
-| **缺陷 2**：长生命周期令牌 | 60s TTL + 90s 宽限，由定时器自动轮换 |
-| **缺陷 3**：可预测的令牌生成 | `crypto.randomBytes(32)` —— 256 位熵。短码采用拒绝采样以消除取模偏差 |
-| **缺陷 4**：客户端令牌生成 | 仅服务端 —— 令牌在嵌入二维码前绝不离开服务器 |
-| **缺陷 5**：缺少状态通知 | 桌面提示：*「设备 [IP] 已通过二维码认证（Safari）。不是你？[吊销]」* —— 实时 QRLjacking 检测 |
-| **缺陷 6**：会话绑定不足 | 存储 IP + User-Agent 以供审计。通过 API 手动吊销会话。HttpOnly + Secure + SameSite=lax cookie |
+| USENIX 缺陷                  | 缓解措施                                                                                      |
+| ---------------------------- | --------------------------------------------------------------------------------------------- |
+| **缺陷 1**：缺少一次性强制   | 令牌首次扫描即原子性消费 —— 重放永远失败                                                      |
+| **缺陷 2**：长生命周期令牌   | 60s TTL + 90s 宽限，由定时器自动轮换                                                          |
+| **缺陷 3**：可预测的令牌生成 | `crypto.randomBytes(32)` —— 256 位熵。短码采用拒绝采样以消除取模偏差                          |
+| **缺陷 4**：客户端令牌生成   | 仅服务端 —— 令牌在嵌入二维码前绝不离开服务器                                                  |
+| **缺陷 5**：缺少状态通知     | 桌面提示：_「设备 [IP] 已通过二维码认证（Safari）。不是你？[吊销]」_ —— 实时 QRLjacking 检测  |
+| **缺陷 6**：会话绑定不足     | 存储 IP + User-Agent 以供审计。通过 API 手动吊销会话。HttpOnly + Secure + SameSite=lax cookie |
 
 #### 时序安全的查找
 
@@ -406,23 +557,23 @@ URL 被刻意保持精简（`/q/` 路径 + 6 字符码 ≈ 53–56 个字符）
 
 #### 威胁覆盖
 
-| 威胁 | 为何无效 |
-|--------|-------------------|
-| **二维码截图被分享** | 一次性：首次扫描即消费。60s TTL：攻击者动手前已过期。桌面通知会立即提醒你。 |
-| **重放攻击** | 原子性一次性消费 + 60s TTL。旧 URL 始终返回 401。 |
+| 威胁                    | 为何无效                                                                             |
+| ----------------------- | ------------------------------------------------------------------------------------ |
+| **二维码截图被分享**    | 一次性：首次扫描即消费。60s TTL：攻击者动手前已过期。桌面通知会立即提醒你。          |
+| **重放攻击**            | 原子性一次性消费 + 60s TTL。旧 URL 始终返回 401。                                    |
 | **Cloudflare 边缘日志** | 短码是不透明的 6 字符查找键，而非真正的 256 位令牌。一次性意味着从日志重放永远失败。 |
-| **暴力破解** | 568 亿种组合、任意时刻约 2 个有效、双层速率限制，早在统计可行性之前就已拦截。 |
-| **QRLjacking** | 60s 轮换迫使实时转发。桌面提示提供即时检测。自托管单用户场景使钓鱼难以成立。 |
-| **时序攻击** | 基于哈希的 Map 查找 —— 无字符串比较时序泄露。 |
-| **会话 cookie 窃取** | HttpOnly + Secure + SameSite=lax + 24h TTL。可在 `POST /api/auth/revoke` 手动吊销。 |
+| **暴力破解**            | 568 亿种组合、任意时刻约 2 个有效、双层速率限制，早在统计可行性之前就已拦截。        |
+| **QRLjacking**          | 60s 轮换迫使实时转发。桌面提示提供即时检测。自托管单用户场景使钓鱼难以成立。         |
+| **时序攻击**            | 基于哈希的 Map 查找 —— 无字符串比较时序泄露。                                        |
+| **会话 cookie 窃取**    | HttpOnly + Secure + SameSite=lax + 24h TTL。可在 `POST /api/auth/revoke` 手动吊销。  |
 
 #### 横向对比
 
-| 平台 | 模型 | 对比 |
-|----------|-------|------------|
-| **Discord** | 长生命周期令牌、无确认、[屡被利用](https://owasp.org/www-community/attacks/Qrljacking) | Codeman：一次性 + TTL + 通知 |
-| **WhatsApp Web** | 手机确认「关联设备？」，约 60s 轮换 | 轮换相当；WhatsApp 额外加了显式确认（对单用户而言是可接受的取舍） |
-| **Signal** | 临时公钥、端到端加密信道 | 加密更强，但 [2025 年仍被俄罗斯国家级行为者](https://cloud.google.com/blog/topics/threat-intelligence/russia-targeting-signal-messenger)通过社会工程攻破 |
+| 平台             | 模型                                                                                   | 对比                                                                                                                                                     |
+| ---------------- | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Discord**      | 长生命周期令牌、无确认、[屡被利用](https://owasp.org/www-community/attacks/Qrljacking) | Codeman：一次性 + TTL + 通知                                                                                                                             |
+| **WhatsApp Web** | 手机确认「关联设备？」，约 60s 轮换                                                    | 轮换相当；WhatsApp 额外加了显式确认（对单用户而言是可接受的取舍）                                                                                        |
+| **Signal**       | 临时公钥、端到端加密信道                                                               | 加密更强，但 [2025 年仍被俄罗斯国家级行为者](https://cloud.google.com/blog/topics/threat-intelligence/russia-targeting-signal-messenger)通过社会工程攻破 |
 
 > 完整设计理由、安全分析与实现细节：[`docs/qr-auth-plan.md`](docs/qr-auth-plan.md)
 
@@ -430,13 +581,14 @@ URL 被刻意保持精简（`/q/` 路径 + 6 字符码 ≈ 53–56 个字符）
 
 ## 安全
 
-Codeman 用 `--dangerously-skip-permissions` 启动会话，因此 Web UI 在设计上对任何能访问到它的人都是一个远程代码执行面 —— 整套安全模型的存在就是为了控制*谁*能访问。近期加固（v0.9.0 + v0.9.5）封堵了那些常困扰自托管开发工具的浏览器驱动攻击路径。完整模型：[`docs/security-architecture.md`](docs/security-architecture.md)。
+Codeman 默认用 `--dangerously-skip-permissions` 启动会话，因此 Web UI 在设计上对任何能访问到它的人都是一个远程代码执行面 —— 整套安全模型的存在就是为了控制*谁*能访问。（启动权限模式可配置，见下文。）近期加固（v0.9.0 + v0.9.5）封堵了那些常困扰自托管开发工具的浏览器驱动攻击路径。完整模型：[`docs/security-architecture.md`](docs/security-architecture.md)。**发现了漏洞？** 私下披露方式与已知限制清单见 [`SECURITY.md`](.github/SECURITY.md)。
 
 ### 网络与访问
 
 - **默认仅环回** —— 绑定 `127.0.0.1`，仅可从本机访问，因此「无密码」默认配置开箱即安全。在未设置 `CODEMAN_PASSWORD` 的情况下绑定非环回主机会*启动但打印一条醒目警告*，并给出三个具体修复方案（设置密码、环回 + 一个带认证的隧道，或用 `--allow-unauthenticated-network` 显式确认）
 - **可选认证，真实会话** —— 通过 `CODEMAN_USERNAME`（默认 `admin`）/ `CODEMAN_PASSWORD` 的 HTTP Basic 认证。成功后签发一个不透明的 256 位 `codeman_session` cookie（`randomBytes(32)`）—— 服务端校验，而非客户端签名，因此无法离线伪造（24h TTL、自动延长、设备上下文审计日志）
 - **按 IP 速率限制** —— 失败 10 次 → `429` 并带 `Retry-After`（15 分钟衰减）。即便攻击者在同一 IP 上猛攻，有效 cookie 或正确密码也能*立即*恢复 —— 这很重要，因为所有隧道流量共享同一个环回 IP。二维码认证有自己独立的限制器
+- **可配置的权限模式**：`--dangerously-skip-permissions` 只是默认值。**App Settings → Claude CLI → Startup Mode** 可以把新会话切换为 Anthropic 的分类器护栏 `auto` 模式（低打扰，需要 Claude Code 2.1.207+）、`normal` 提示模式，或一份显式的允许工具列表。多用户模式下，未获授权的用户会被强制为 `auto`，shell 会话与跳过权限需要按用户显式授权
 
 ### 始终开启的浏览器加固（v0.9.5）
 
@@ -450,7 +602,7 @@ Codeman 用 `--dangerously-skip-permissions` 启动会话，因此 Web UI 在设
 
 ### 输入、文件与响应头
 
-- **模式校验的输入** —— 每个 API 请求体都用 Zod v4 模式检查；一个 `CLAUDE_CODE_*` / `OPENCODE_*` / `CODEX_*` 环境变量前缀允许列表把控每个 CLI 能接收哪些设置
+- **模式校验的输入** —— 每个 API 请求体都用 Zod v4 模式检查；一个 `CLAUDE_CODE_*` / `OPENCODE_*` / `CODEX_*` / `GEMINI_*` / `GOOGLE_*` 环境变量前缀允许列表把控每个 CLI 能接收哪些设置
 - **路径限定** —— 文件路由在边界检查前先 `realpath`（无 TOCTOU）；`..`、绝对路径、以及解析到工作目录之外的符号链接都会被拒绝。上限：10 MB 文本预览 / 50 MB 原始与下载；`/api/download` 对敏感路径（`.env`、`*credentials*`、`~/.ssh/`、`.aws/credentials`）做黑名单。SVG/HTML 以 `octet-stream` + `nosniff` + attachment 提供，因此会被下载而非执行
 - **安全响应头** —— `Content-Security-Policy`（`default-src 'self'`，每个例外都逐条列举）、`X-Content-Type-Options: nosniff`、`X-Frame-Options: SAMEORIGIN`、HTTPS 下的 HSTS，以及**仅**对 `localhost` / `127.0.0.1` / `::1` 反射的 CORS
 
@@ -481,73 +633,172 @@ sc -l           # 列出会话
 
 > Ctrl 绑定在 macOS 上也接受 Cmd。
 
-| 快捷键 | 动作 |
-|----------|--------|
-| `Ctrl/Cmd+W` | 杀掉当前会话 |
-| `Ctrl/Cmd+Tab` | 下一个会话 |
-| `Alt+1`–`Alt+9` | 切换到第 N 个标签 |
-| `Ctrl+Shift+{` / `Ctrl+Shift+}` | 将当前标签左移 / 右移 |
-| `Ctrl/Cmd+L` | 清屏 |
-| `Ctrl+Shift+R` | 恢复终端尺寸 |
-| `Ctrl+Shift+V` | 切换语音输入 |
-| `Ctrl/Cmd +` / `-` | 字体大小 |
-| `Ctrl/Cmd+?` | 键盘帮助 |
-| `Shift+Enter` | 插入换行（发送到终端） |
-| `Escape` | 关闭面板与模态框 |
+| 快捷键                          | 动作                                                     |
+| ------------------------------- | -------------------------------------------------------- |
+| `Ctrl/Cmd+W`                    | 杀掉当前会话                                             |
+| `Ctrl/Cmd/Option+K`             | 查找已打开的会话或新建一个                               |
+| `Ctrl/Cmd+Tab`                  | 下一个会话                                               |
+| `Alt/Option+[` / `Alt/Option+]` | 上一个 / 下一个会话                                      |
+| `Alt/Option+1`–`Alt/Option+9`   | 切换到第 N 个标签（按物理键位，macOS Option 布局也适用） |
+| `Ctrl+Shift+{` / `Ctrl+Shift+}` | 将当前标签左移 / 右移                                    |
+| `Ctrl/Cmd+L`                    | 清屏                                                     |
+| `Ctrl+Shift+R`                  | 恢复终端尺寸                                             |
+| `Ctrl+Shift+V`                  | 切换语音输入                                             |
+| `Ctrl/Cmd +` / `-`              | 字体大小                                                 |
+| `Ctrl/Cmd+?`                    | 键盘帮助                                                 |
+| `Shift+Enter`                   | 插入换行（发送到终端）                                   |
+| `Escape`                        | 关闭面板与模态框                                         |
+
+---
+
+## 从智能体驱动 Codeman —— 编程指南
+
+面向不经浏览器控制 Codeman 的 AI 智能体与自动化：一个拉起工作会话的智能体、一个 CI 机器人，或是**运行在 Codeman 会话*内部*、编排其他会话的 Claude Code**。UI 能做的一切都是 HTTP + CLI，因此智能体也能做。
+
+### 检测自己身处 Codeman 内部
+
+当 CLI 运行在 Codeman 受管会话中时，以下环境变量会被设置 —— 读取它们，别硬编码任何东西：
+
+| 变量                       | 含义                                                                                                                 |
+| -------------------------- | -------------------------------------------------------------------------------------------------------------------- |
+| `CODEMAN_MUX=1`            | 你在一个受管 tmux 会话里。**绝不要** `tmux kill-session` / `pkill claude` / `pkill tmux` —— 你会杀掉自己或兄弟会话。 |
+| `CODEMAN_API_URL`          | API 的基础 URL（例如 `https://127.0.0.1:3000`）。下面每个调用都用它。                                                |
+| `CODEMAN_SESSION_ID`       | *你自己的*会话 id。用它避免对自己下手。                                                                              |
+| `CODEMAN_HOOK_SECRET_FILE` | hook 密钥文件的路径（受管隧道开启时调用 `/api/hook-event` 必需）。                                                   |
+
+### 行路规则（POST 之前先读）
+
+1. **只发单行输入。** 编程输入会作为字面文本 **+ Enter** 一次性发送。多行字符串会破坏智能体 TUI（Ink）—— 发送一行，或拆成多次调用。
+2. **让输入幂等。** 在 `POST …/input` 上带上稳定的 `clientId` 和按会话单调递增的 `seq`。服务端会去重，因此连接中断后的重试不会重复投递提示。
+3. **认证。** 若设置了 `CODEMAN_PASSWORD`，发送 HTTP Basic 认证（用户 `admin` 或 `CODEMAN_USERNAME`）或 `codeman_session` cookie。默认的环回安装无密码。缺失的 `Origin` 头被允许，因此普通 `curl` 可用；跨站的浏览器 origin 会被拒绝（CSRF 防护）。
+4. **响应信封。** 多数端点返回 `{ "success": true, "data": … }`（错误：`{ "success": false, "error", "errorCode" }`）。少数遗留 GET 返回裸响应体 —— **两种都要处理**（`body.data ?? body`）。
+5. **`/api/v1/*`** 是 `/api/*` 的稳定别名。
+
+### 常用配方
+
+```bash
+API="${CODEMAN_API_URL:-http://127.0.0.1:3000}"
+# （若设置了密码，给每个调用加上  -u admin:"$CODEMAN_PASSWORD"）
+
+# 1. 看看有什么在运行
+curl -s "$API/api/sessions" | jq '.data // .'
+
+# 2. 拉起一个工作会话（「case」= 命名工作目录）
+curl -s -X POST "$API/api/quick-start" \
+  -H 'Content-Type: application/json' \
+  -d '{"caseName":"refactor-auth","mode":"claude","effort":"high"}' | jq
+
+# 3. 向会话发送提示（精确一次：clientId + seq）
+curl -s -X POST "$API/api/sessions/$SID/input" \
+  -H 'Content-Type: application/json' \
+  -d '{"input":"Run the test suite and summarize failures","useMux":true,"clientId":"agent-1","seq":1}'
+
+# 4. 读回终端内容
+curl -s "$API/api/sessions/$SID/output" | jq -r '.data // .'
+
+# 5. 流式接收实时事件（会话输出、智能体活动、状态）
+curl -sN "$API/api/events"          # Server-Sent Events
+
+# 6. 调度周期性工作（cron 风格任务）
+curl -s -X POST "$API/api/cron/jobs" \
+  -H 'Content-Type: application/json' \
+  -d '{"name":"nightly-deps","agentType":"claude","workingDir":"/home/me/proj",
+       "promptMode":"inline_text","promptText":"Update dependencies and open a PR",
+       "inputMode":"typed","scheduleType":"daily","dailyTime":"03:00",
+       "enabled":true,"concurrencyPolicy":"warn_only"}' | jq
+
+# 7. 查看后台子智能体及其活动记录
+curl -s "$API/api/subagents" | jq '.data // .'
+curl -s "$API/api/subagents/$AID/transcript" | jq -r '.data // .'
+
+# 8. 全系统快照（会话、设置、重生、统计）
+curl -s "$API/api/status" | jq
+```
+
+### 或使用内置 CLI
+
+同样的操作也有命令形式（`codeman <cmd>`，括号内为别名）—— 在会话内的 shell 工具里很顺手：
+
+```bash
+codeman session start -d /path/to/repo   # (s)  启动会话
+codeman session list                     #      列出会话
+codeman session logs <id>                #      查看输出
+codeman task add "fix the failing test"  # (t)  排入任务
+codeman attach <path>                    #      附着 Claude hook 上下文
+```
+
+### Hook（事件*回流*到 Codeman）
+
+Codeman 会注册 Claude Code hook，它们 `POST /api/hook-event`（`permission_prompt`、`idle_prompt`、`stop`、`task_completed` 等），让仪表盘实时响应。该端点在环回上免认证，但在受管隧道下需要 `X-Codeman-Hook-Secret` 头（从 `$CODEMAN_HOOK_SECRET_FILE` 读取）。通常你不需要手动调用它 —— Codeman 会自动接好 —— 但自主层正是靠它「看见」智能体在做什么。
+
+> 完整端点列表与请求/响应形状见下文。
 
 ---
 
 ## API
 
-基于 Fastify 的 REST —— **15 个路由模块中约 140 个处理器**，外加一条 SSE 流和一条 WebSocket 终端通道。以下是一个有代表性的子集：
+基于 Fastify 的 REST —— **20 个路由模块中约 190 个处理器**，外加一条 SSE 流和一条 WebSocket 终端通道。所有响应都使用 `ApiResponse<T>` 信封（`{success, data}` / `{success, error, errorCode}`）；`/api/v1/*` 是稳定别名。以下是一个有代表性的子集：
 
 ### 会话（Sessions）
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `GET` | `/api/sessions` | 列出全部 |
-| `POST` | `/api/quick-start` | 创建 case 并启动会话 |
-| `DELETE` | `/api/sessions/:id` | 删除会话 |
-| `POST` | `/api/sessions/:id/input` | 发送输入 |
+
+| 方法     | 端点                       | 说明                                                                           |
+| -------- | -------------------------- | ------------------------------------------------------------------------------ |
+| `GET`    | `/api/sessions`            | 列出全部                                                                       |
+| `POST`   | `/api/quick-start`         | 创建 case + 启动会话（`{caseName?, mode?, effort?, envOverrides?}`）           |
+| `POST`   | `/api/sessions/:id/input`  | 发送输入（`{input, useMux?, clientId?, seq?}` —— `clientId`+`seq` = 精确一次） |
+| `GET`    | `/api/sessions/:id/output` | 读取终端输出                                                                   |
+| `GET`    | `/api/sessions/unified`    | 统一的活动 + 历史清单（会话管理器）：`?q=&limit=`                              |
+| `POST`   | `/api/sessions/:id/pin`    | 在会话管理器中置顶 / 取消置顶（`{pinned}`）                                    |
+| `PUT`    | `/api/session-order`       | 跨设备同步标签顺序（`{order: [ids]}`）                                         |
+| `DELETE` | `/api/sessions/:id`        | 删除会话                                                                       |
 
 ### 重生（Respawn）
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `POST` | `/api/sessions/:id/respawn/enable` | 启用，带配置与定时器 |
-| `POST` | `/api/sessions/:id/respawn/stop` | 停止控制器 |
-| `PUT` | `/api/sessions/:id/respawn/config` | 更新配置 |
 
-### Ralph / Todo
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `GET` | `/api/sessions/:id/ralph-state` | 获取循环状态 + todos |
-| `POST` | `/api/sessions/:id/ralph-config` | 配置跟踪 |
+| 方法   | 端点                               | 说明                 |
+| ------ | ---------------------------------- | -------------------- |
+| `POST` | `/api/sessions/:id/respawn/enable` | 启用，带配置与定时器 |
+| `POST` | `/api/sessions/:id/respawn/stop`   | 停止控制器           |
+| `PUT`  | `/api/sessions/:id/respawn/config` | 更新配置             |
 
 ### 编排器（Orchestrator）
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `POST` | `/api/orchestrator/start` | 从目标启动编排 |
-| `POST` | `/api/orchestrator/approve` | 批准生成的计划 |
-| `GET` | `/api/orchestrator/status` | 当前阶段 + 进度 |
-| `POST` | `/api/orchestrator/stop` | 停止并清理 |
+
+| 方法   | 端点                        | 说明            |
+| ------ | --------------------------- | --------------- |
+| `POST` | `/api/orchestrator/start`   | 从目标启动编排  |
+| `POST` | `/api/orchestrator/approve` | 批准生成的计划  |
+| `GET`  | `/api/orchestrator/status`  | 当前阶段 + 进度 |
+| `POST` | `/api/orchestrator/stop`    | 停止并清理      |
+
+### Cron（定时任务）
+
+| 方法             | 端点                         | 说明                  |
+| ---------------- | ---------------------------- | --------------------- |
+| `GET` / `POST`   | `/api/cron/jobs`             | 列出 / 创建 cron 任务 |
+| `PUT` / `DELETE` | `/api/cron/jobs/:id`         | 更新 / 删除任务       |
+| `PUT`            | `/api/cron/jobs/:id/enabled` | 启用 / 禁用           |
+| `POST`           | `/api/cron/jobs/:id/run`     | 立即运行              |
+| `GET`            | `/api/cron/jobs/:id/runs`    | 运行历史              |
 
 ### 子智能体（Subagents）
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `GET` | `/api/subagents` | 列出所有后台智能体 |
-| `GET` | `/api/subagents/:id` | 智能体信息与状态 |
-| `GET` | `/api/subagents/:id/transcript` | 完整活动记录 |
-| `DELETE` | `/api/subagents/:id` | 杀掉智能体进程 |
+
+| 方法     | 端点                            | 说明               |
+| -------- | ------------------------------- | ------------------ |
+| `GET`    | `/api/subagents`                | 列出所有后台智能体 |
+| `GET`    | `/api/subagents/:id`            | 智能体信息与状态   |
+| `GET`    | `/api/subagents/:id/transcript` | 完整活动记录       |
+| `DELETE` | `/api/subagents/:id`            | 杀掉智能体进程     |
 
 ### 系统（System）
-| 方法 | 端点 | 说明 |
-|--------|----------|-------------|
-| `GET` | `/api/events` | SSE 流 |
-| `GET` | `/api/status` | 完整应用状态 |
-| `POST` | `/api/hook-event` | Hook 回调 |
-| `GET` | `/api/system/update/check` | 检查新发行版 |
-| `POST` | `/api/system/update` | 自更新（git-clone 安装） |
-| `POST` | `/api/clipboard` | 把文本推送到所有已连接浏览器（`{text}`） |
-| `GET` | `/api/sessions/:id/run-summary` | 时间线 + 统计 |
+
+| 方法   | 端点                            | 说明                                     |
+| ------ | ------------------------------- | ---------------------------------------- |
+| `GET`  | `/api/events`                   | SSE 流                                   |
+| `GET`  | `/api/status`                   | 完整应用状态                             |
+| `POST` | `/api/hook-event`               | Hook 回调                                |
+| `GET`  | `/api/system/update/check`      | 检查新发行版                             |
+| `POST` | `/api/system/update`            | 自更新（git-clone 安装）                 |
+| `POST` | `/api/clipboard`                | 把文本推送到所有已连接浏览器（`{text}`） |
+| `GET`  | `/api/sessions/:id/run-summary` | 时间线 + 统计                            |
 
 ---
 
@@ -571,7 +822,6 @@ flowchart TB
         end
 
         subgraph Detection["检测层"]
-            RT["Ralph 跟踪器"]
             SW["子智能体监视器<br/><small>~/.claude/projects/*/subagents</small>"]
             TW["团队监视器<br/><small>~/.claude/teams/*</small>"]
         end
@@ -582,7 +832,7 @@ flowchart TB
         end
 
         subgraph External["外部"]
-            CLI["AI CLI<br/><small>Claude Code / OpenCode / Codex</small>"]
+            CLI["AI CLI<br/><small>Claude Code / OpenCode / Codex / Gemini</small>"]
             BG["后台智能体<br/><small>(Task 工具)</small>"]
         end
     end
@@ -595,7 +845,6 @@ flowchart TB
     SM --> RC
     SM --> ORC
     SM --> SS
-    S1 --> RT
     S1 --> SCR
     S2 --> SCR
     RC --> SCR
@@ -614,7 +863,7 @@ flowchart TB
 npm install
 npx tsx src/index.ts web    # 开发模式
 npm run build               # 生产构建
-npm test                    # 运行测试
+npm run test:ci             # 运行测试（CI 套件；浏览器套件需要额外环境）
 ```
 
 完整文档见 [CLAUDE.md](./CLAUDE.md)。
@@ -625,14 +874,14 @@ npm test                    # 运行测试
 
 本代码库经历了一次全面的 7 阶段重构，消除了上帝对象、集中了配置，并建立了模块化架构：
 
-| 阶段 | 改了什么 | 影响 |
-|-------|-------------|--------|
-| **性能** | 缓存端点、SSE 自适应批处理、缓冲区分块 | 终端延迟低于 16ms |
-| **路由抽取** | `server.ts` 拆分为 15 个领域路由模块 + 认证中间件 + 端口接口 | server.ts 代码量 **−67%**（6,736 → 2,254） |
-| **领域拆分** | `types.ts` → 16 个领域文件、`ralph-tracker` → 7 个文件、`respawn-controller` → 5 个文件、`session` → 6 个文件 | 不再有上帝文件 |
-| **前端模块** | `app.js` → 18 个抽取模块，横跨基础设施、领域与特性层 | app.js 核心降至 **约 3.4K 行** |
-| **配置合并** | 约 70 个散落的魔法数字 → 10 个领域聚焦的配置文件 | 零跨文件重复 |
-| **测试基础设施** | 共享 mock 库、12 个路由测试文件、统一的 MockSession | 路由处理器可通过 `app.inject()` 测试 |
+| 阶段             | 改了什么                                                                                                      | 影响                                       |
+| ---------------- | ------------------------------------------------------------------------------------------------------------- | ------------------------------------------ |
+| **性能**         | 缓存端点、SSE 自适应批处理、缓冲区分块                                                                        | 终端延迟低于 16ms                          |
+| **路由抽取**     | `server.ts` 拆分为 15 个领域路由模块 + 认证中间件 + 端口接口                                                  | server.ts 代码量 **−67%**（6,736 → 2,254） |
+| **领域拆分**     | `types.ts` → 16 个领域文件、`ralph-tracker` → 7 个文件、`respawn-controller` → 5 个文件、`session` → 6 个文件 | 不再有上帝文件                             |
+| **前端模块**     | `app.js` → 18 个抽取模块，横跨基础设施、领域与特性层                                                          | app.js 核心降至 **约 3.4K 行**             |
+| **配置合并**     | 约 70 个散落的魔法数字 → 10 个领域聚焦的配置文件                                                              | 零跨文件重复                               |
+| **测试基础设施** | 共享 mock 库、12 个路由测试文件、统一的 MockSession                                                           | 路由处理器可通过 `app.inject()` 测试       |
 
 完整细节：[`docs/archive/code-structure-findings.md`](docs/archive/code-structure-findings.md)
 
@@ -654,6 +903,10 @@ npm install xterm-zerolag-input
 
 ---
 
+## 版本策略
+
+Codeman 遵循 [SemVer](https://semver.org/)。版本号真正承诺的内容，以及哪些算内部实现（HTTP/SSE API、磁盘上的状态、实验性特性），都写在 [`docs/versioning-policy.md`](docs/versioning-policy.md) 中。如果你的脚本依赖 HTTP API，请锁定到确切版本。
+
 ## 许可证
 
 MIT —— 见 [LICENSE](LICENSE)

docker/agent.Dockerfile

@@ -40,9 +40,20 @@ RUN npm install -g \
 # runtime Codeman overrides with `--user <hostUid>:0` on Linux, so the baked uid
 # only matters for a hand-run / Docker Desktop container. gid 0 + group-writable
 # HOME (OpenShift arbitrary-uid convention) keeps $HOME writable for any uid.
+# UTF-8 locale so tmux/Ink render Unicode box-drawing instead of VT100 ACS `q`
+# glyphs (C.UTF-8 is built into glibc; no locales package needed). Codeman also
+# sets these at run time so containers built before this line still get UTF-8.
+ENV LANG=C.UTF-8 LC_ALL=C.UTF-8
 ENV HOME=/home/agent
+# `.claude` (+ `.claude/projects` mount point) and `.codex` (+ `.codex/sessions`) are
+# pre-created gid-0 group-writable so the container owns its OWN credential config
+# dirs: tokens/settings/config are seeded in as writable copies and each CLI's runtime
+# state (backups, tasks, refreshed tokens) stays container-local, while ONLY the shared
+# transcript/rollout dirs (`.claude/projects`, `.codex/sessions`) are bind-mounted from
+# the host. (gemini/gcloud/opencode are whole seed-copies and need no pre-created dir.)
 RUN useradd -g 0 -m -d /home/agent -s /bin/bash agent \
  && mkdir -p /home/agent/.npm /home/agent/.cache /home/agent/.config /home/agent/.codeman \
+      /home/agent/.claude/projects /home/agent/.codex/sessions \
  && chgrp -R 0 /home/agent \
  && chmod -R g=u /home/agent
 

docs/claude-code-hooks-reference.md

@@ -2,14 +2,18 @@
 
 > Official documentation for Claude Code hooks system, extracted from [code.claude.com](https://code.claude.com/docs/en/hooks).
 
-**Last Updated**: 2026-01-24
+**Last Updated**: 2026-07-25
 **Source**: [Claude Code Hooks Documentation](https://code.claude.com/docs/en/hooks)
 
+> This is a maintained summary, not an exhaustive copy of the upstream reference.
+> Check the source link for event-specific schemas before adding a new hook.
+
 ---
 
 ## Overview
 
 Hooks are automated scripts that execute at specific events during your Claude Code session. They allow you to:
+
 - Validate, modify, or block tool usage
 - Add context to prompts
 - Implement custom workflows
@@ -21,12 +25,12 @@ Hooks are automated scripts that execute at specific events during your Claude C
 
 Hooks are configured in settings files:
 
-| File | Scope |
-|------|-------|
-| `~/.claude/settings.json` | User (global) |
-| `.claude/settings.json` | Project |
+| File                          | Scope                      |
+| ----------------------------- | -------------------------- |
+| `~/.claude/settings.json`     | User (global)              |
+| `.claude/settings.json`       | Project                    |
 | `.claude/settings.local.json` | Local project (gitignored) |
-| Plugin hook files | Plugin-specific |
+| Plugin hook files             | Plugin-specific            |
 
 ### Basic Structure
 
@@ -49,8 +53,9 @@ Hooks are configured in settings files:
 ```
 
 **Key Fields**:
+
 - `matcher`: Pattern to match tool names (case-sensitive, supports regex like `Edit|Write` or `*` for all)
-- `type`: `"command"` for bash or `"prompt"` for LLM-based evaluation
+- `type`: `"command"`, `"http"`, `"mcp_tool"`, `"prompt"`, or `"agent"` where the event supports it
 - `command`: Bash command to execute
 - `prompt`: LLM prompt for evaluation (prompt-based hooks only)
 - `timeout`: Optional timeout in seconds (default: 60)
@@ -59,6 +64,10 @@ Hooks are configured in settings files:
 
 ## Hook Events
 
+Claude Code's current event surface is broader than the detailed subset below. In
+particular, `TeammateIdle` and `TaskCompleted` are supported lifecycle events used
+by Codeman; they are not stale or plugin-defined event names.
+
 ### PreToolUse
 
 **When**: After Claude creates tool parameters, before processing the tool call.
@@ -66,15 +75,17 @@ Hooks are configured in settings files:
 **Use Cases**: Approval, denial, or modification of tool calls.
 
 **Common Matchers**:
+
 - `Bash` - Shell commands
 - `Write` - File writing
 - `Edit` - File editing
 - `Read` - File reading
-- `Task` - Subagent tasks
+- `Agent` - Subagent tasks
 - `WebFetch`, `WebSearch` - Web operations
 - `mcp__<server>__<tool>` - MCP tools
 
 **Output Control**:
+
 ```json
 {
   "hookSpecificOutput": {
@@ -96,13 +107,14 @@ Hooks are configured in settings files:
 **Use Cases**: Auto-approve or deny permissions.
 
 **Output Control**:
+
 ```json
 {
   "hookSpecificOutput": {
     "hookEventName": "PermissionRequest",
     "decision": {
       "behavior": "allow|deny",
-      "updatedInput": { },
+      "updatedInput": {},
       "message": "deny reason",
       "interrupt": false
     }
@@ -117,6 +129,7 @@ Hooks are configured in settings files:
 **Use Cases**: Provide feedback, run formatters/linters, log operations.
 
 **Output Control**:
+
 ```json
 {
   "decision": "block",
@@ -128,15 +141,30 @@ Hooks are configured in settings files:
 }
 ```
 
+#### Asynchronous Rewake
+
+Command hooks can set `"asyncRewake": true` to run asynchronously and wake an
+idle Claude turn when the hook exits with code 2. The hook's stderr is delivered
+to Claude as a system reminder. This implies `"async": true`; ordinary async
+hooks do not wake an idle turn, and their output waits for the next interaction.
+
+Codeman uses this on `PostToolUse(Bash)`: a self-contained Node helper extracts
+the background task ID from the Bash result, watches the session transcript for
+the matching completion notification, and exits 2. It does not send terminal
+input, so it cannot submit a user's partially written prompt.
+
 ### Notification
 
 **When**: When Claude Code sends notifications.
 
 **Matchers**:
+
 - `permission_prompt`
 - `idle_prompt`
 - `auth_success`
 - `elicitation_dialog`
+- `elicitation_complete`
+- `elicitation_response`
 
 ### UserPromptSubmit
 
@@ -145,6 +173,7 @@ Hooks are configured in settings files:
 **Use Cases**: Add context, validate, or block prompts.
 
 **Output Control**:
+
 ```json
 {
   "decision": "block",
@@ -165,6 +194,7 @@ Hooks are configured in settings files:
 **Use Cases**: **Ralph Wiggum loops** - block exit and refeed prompt.
 
 **Output Control**:
+
 ```json
 {
   "decision": "block",
@@ -173,6 +203,7 @@ Hooks are configured in settings files:
 ```
 
 Or to allow exit:
+
 ```json
 {
   "continue": true,
@@ -184,15 +215,32 @@ Or to allow exit:
 
 ### SubagentStop
 
-**When**: When a subagent (Task tool call) finishes responding.
+**When**: When a subagent (Agent tool call) finishes responding.
 
 **Use Cases**: Control nested loops, verify subagent output.
 
+### TeammateIdle
+
+**When**: When an agent-team teammate is about to go idle.
+
+**Use Cases**: Reassign work, continue a teammate loop, or notify an orchestrator.
+
+**Matcher Support**: None. The hook fires for every occurrence.
+
+### TaskCompleted
+
+**When**: When a task is about to be marked completed.
+
+**Use Cases**: Validate completion or forward team progress to an external UI.
+
+**Matcher Support**: None. The hook fires for every occurrence.
+
 ### PreCompact
 
 **When**: Before a compact operation.
 
 **Matchers**:
+
 - `manual` - Invoked from `/compact`
 - `auto` - Invoked from auto-compact
 
@@ -201,6 +249,7 @@ Or to allow exit:
 **When**: When Claude Code starts or resumes a session.
 
 **Matchers**:
+
 - `startup` - Fresh start
 - `resume` - From `--resume`, `--continue`, or `/resume`
 - `clear` - From `/clear`
@@ -209,6 +258,7 @@ Or to allow exit:
 **Use Cases**: Load development context, set environment variables.
 
 **Persisting Environment Variables**:
+
 ```bash
 #!/bin/bash
 if [ -n "$CLAUDE_ENV_FILE" ]; then
@@ -219,6 +269,7 @@ exit 0
 ```
 
 **Output Control**:
+
 ```json
 {
   "hookSpecificOutput": {
@@ -233,6 +284,7 @@ exit 0
 **When**: When a session ends.
 
 **Reason Values**:
+
 - `clear`
 - `logout`
 - `prompt_input_exit`
@@ -254,7 +306,7 @@ Hooks receive JSON via stdin with common fields:
   "permission_mode": "default",
   "hook_event_name": "PreToolUse",
   "tool_name": "Bash",
-  "tool_input": { },
+  "tool_input": {},
   "tool_use_id": "toolu_01ABC123..."
 }
 ```
@@ -262,6 +314,7 @@ Hooks receive JSON via stdin with common fields:
 ### Tool-Specific Input
 
 **Bash**:
+
 ```json
 {
   "tool_name": "Bash",
@@ -274,6 +327,7 @@ Hooks receive JSON via stdin with common fields:
 ```
 
 **Write**:
+
 ```json
 {
   "tool_name": "Write",
@@ -285,6 +339,7 @@ Hooks receive JSON via stdin with common fields:
 ```
 
 **Edit**:
+
 ```json
 {
   "tool_name": "Edit",
@@ -302,11 +357,11 @@ Hooks receive JSON via stdin with common fields:
 
 ### Exit Codes
 
-| Code | Behavior |
-|------|----------|
-| 0 | Success. `stdout` processed (shown in verbose or added as context) |
-| 2 | Blocking error. Only `stderr` used. Blocks tool/prompt based on event |
-| Other | Non-blocking error. `stderr` shown in verbose, execution continues |
+| Code  | Behavior                                                              |
+| ----- | --------------------------------------------------------------------- |
+| 0     | Success. `stdout` processed (shown in verbose or added as context)    |
+| 2     | Blocking error. Only `stderr` used. Blocks tool/prompt based on event |
+| Other | Non-blocking error. `stderr` shown in verbose, execution continues    |
 
 ### JSON Output (Exit Code 0)
 
@@ -323,7 +378,12 @@ Hooks receive JSON via stdin with common fields:
 
 ## Prompt-Based Hooks
 
-For Stop and SubagentStop events, you can use LLM-based evaluation:
+Prompt and agent handlers are supported by decision-oriented events including
+`PreToolUse`, `PermissionRequest`, `PostToolUse`, `PostToolUseFailure`,
+`PostToolBatch`, `UserPromptSubmit`, `Stop`, `SubagentStop`, `TaskCreated`, and
+`TaskCompleted`. Check the upstream reference before choosing a handler type.
+
+For example, a Stop event can use LLM-based evaluation:
 
 ```json
 {
@@ -344,6 +404,7 @@ For Stop and SubagentStop events, you can use LLM-based evaluation:
 ```
 
 **LLM Response Format**:
+
 ```json
 {
   "ok": true,
@@ -362,17 +423,18 @@ Hooks can be defined in Skills, Agents, and Slash Commands using frontmatter:
 name: secure-operations
 hooks:
   PreToolUse:
-    - matcher: "Bash"
+    - matcher: 'Bash'
       hooks:
         - type: command
-          command: "./scripts/security-check.sh"
+          command: './scripts/security-check.sh'
 ---
 ```
 
 These hooks:
+
 - Are scoped to the component's lifecycle
 - Only run when that component is active
-- Support: PreToolUse, PostToolUse, Stop
+- Support all hook events; a subagent-scoped `Stop` is converted to `SubagentStop`
 
 ---
 
@@ -550,11 +612,11 @@ exit 0
 
 ## Environment Variables
 
-| Variable | Description |
-|----------|-------------|
-| `CLAUDE_PROJECT_DIR` | Project root directory |
-| `CLAUDE_CODE_REMOTE` | `"true"` for web, empty for CLI |
-| `CLAUDE_ENV_FILE` | Path to write persistent env vars (SessionStart) |
+| Variable             | Description                                      |
+| -------------------- | ------------------------------------------------ |
+| `CLAUDE_PROJECT_DIR` | Project root directory                           |
+| `CLAUDE_CODE_REMOTE` | `"true"` for web, empty for CLI                  |
+| `CLAUDE_ENV_FILE`    | Path to write persistent env vars (SessionStart) |
 
 ---
 
@@ -593,4 +655,4 @@ Use `/hooks` command to view registered hooks and make changes.
 
 ---
 
-*Source: [Claude Code Hooks Documentation](https://code.claude.com/docs/en/hooks)*
+_Source: [Claude Code Hooks Documentation](https://code.claude.com/docs/en/hooks)_

docs/docker-cases.md

@@ -52,8 +52,9 @@ curl -X POST localhost:3000/api/quick-start -d '{"caseName":"sandbox","mode":"cl
 ## Lifecycle
 
 - **Reconnect after a Codeman restart** lands back in the same live agent (the in-container tmux survives).
-- **Container stop / host reboot** recreates the container and, when a resume id was captured, **resumes** the last conversation from the bind-mounted transcript.
+- **Container stop / host reboot** restarts the container and **resumes** the last conversation from the bind-mounted transcript. Claude sessions launch with a pinned conversation id (`--session-id <sessionId>`, with a `--resume` fallback when the transcript already exists), and the case remembers its last conversation (`lastClaudeSessionId`), so a relaunch after the container was stopped, rebooted, or recreated continues where it left off.
 - **Killing one session** only kills that session's in-container tmux session; the shared container stays up for sibling sessions.
+- **Editing the docker host config** (image, memory, network, ...) is detected on the next launch: the desired config hash is compared against the container's `codeman.confighash` label, and a mismatch refuses the launch with a "config changed, recreate?" confirm. Confirming calls `POST /api/docker-cases/:name/recreate` (refused while sessions of the case are live), which removes the container so the next launch recreates it with the new config; the workspace and the conversation survive.
 - **Deleting the case** `docker rm -f`s the container (the bind-mounted workspace on the host survives). An instance-scoped boot reaper removes containers whose case is gone.
 
 ## Isolation & security

docs/multi-user-plan.md

@@ -0,0 +1,282 @@
+# Multi-User Mode: Design Plan
+
+Status: **IMPLEMENTED on `feat/multiuser-mode`** (phases 1-5; opt-in, off by default). Target: opt-in multi-user support behind a `--multiuser` flag, with per-user case spaces and an admin panel for user management.
+
+Shipped by phase:
+
+- **Phase 1** (user store + mode plumbing + CLI): `src/user-store.ts` (scrypt, atomic 0600 writes, last-admin invariants, serialized read-modify-write), `src/config/multiuser.ts`, `codeman users add|passwd|list|rm`, `--multiuser` flag, bootstrap-on-first-boot. Tests: `test/user-store.test.ts`.
+- **Phase 2** (multi-user auth): parallel async auth branch (`src/web/middleware/auth.ts`), `req.authUser`, per-username rate bucket, `mustChangePassword` lockbox, `GET /api/me` + `POST /api/me/password`, QR identity-bound minting, network-bind + tunnel exemptions, new error codes. Tests: `test/multiuser-auth.test.ts`.
+- **Phase 3** (ownership threading): `Session.owner` at every create path + recovery mirror; `findSessionOrFail` owner check + list filtering; §6.3 permission policy (`resolveClaudeModeForUser` at all spawn sites incl. one-shots via `buildPromptArgs`; shell/launchCommand grant); per-user case spaces (`resolveCasesDir`) + owner-scoped case list + admin-only host CRUD; `workingDir` confinement; `sessionCapacityState` per-user cap. Tests: `test/ownership-scoping.test.ts`.
+- **Phase 4** (event fan-out): WS owner gate; SSE per-client identity + `broadcast`/terminal-batch routing (`deriveSseHint`, fail-closed); `getLightState` per-identity filtering; file-route preview/thumbnail/history + `GET /api/search` scoping.
+- **Phase 5** (admin API + frontend): `src/web/routes/admin-routes.ts` (user CRUD, one-time passwords, last-admin guards, session revoke/kill) + `src/web/admin-audit.ts`; `public/admin-ui.js` (identity boot, change-password modal + interceptor, admin Users tab). Tests: `test/admin-routes.test.ts`, `test/admin-ui.test.ts`.
+
+Deferred follow-ups (documented, non-blocking): away-digest + subagent/workflow REST-list scoping, push-subscription identity/routing, per-user screenshot subdirs, `linked-cases.json` v2 owner field, `ScheduledRun.owner`, plan-orchestrator internal one-shot mode resolution, and a Playwright browser pass. Phase 6 (login form replacing Basic) remains out of scope.
+
+## 1. Summary
+
+Today Codeman is strictly single-user: one optional credential pair (`CODEMAN_USERNAME`/`CODEMAN_PASSWORD`), one shared `~/codeman-cases` folder, one global session list, and a global SSE/WS fan-out. This plan adds an opt-in **multi-user mode**:
+
+- **Off by default.** Without the flag, behavior stays byte-identical to today (same auth path, same paths, same payloads). All new code is gated behind `isMultiUserMode()`.
+- **`codeman web --multiuser`** (or `CODEMAN_MULTIUSER=1`) enables named users with individually hashed passwords stored in `~/.codeman/users.json`.
+- **Each user gets their own space**: `~/codeman-users/<username>/cases/<case>` replaces the shared `~/codeman-cases` for that user. Sessions, cases, attachments, search, digests, and SSE events are scoped to their owner.
+- **Admin panel** (App Settings, admin-only "Users" tab): create/delete users, change/reset passwords, enable/disable accounts, delete a user's space, see per-user live sessions and disk usage, force logout.
+
+## 2. Threat Model (read first, be honest about this)
+
+Multi-user mode is **workspace separation for a trusted team, NOT security isolation between mutually distrusting users**:
+
+- Every session still runs as the **same OS account** with `claude --dangerously-skip-permissions`. Any user can ask their agent to `cat /home/<host>/codeman-users/otheruser/...`. The web layer enforces scoping; the agent layer cannot.
+- **Shell sessions and custom launch commands are the bluntest holes**: `SessionMode = 'shell'` hands out a raw shell as the host account, and a cron job's `launchCommand` runs an arbitrary command; no Claude permission classifier is involved in either. These must be gated behind the same grant as bypass (section 6.3), otherwise the `auto`-mode mitigation below is theater.
+- All sessions share one tmux socket (`-L codeman`), one `~/.claude` (transcripts, credentials, plan usage), one Claude subscription.
+- Mitigation for stronger isolation: pair a user's cases with **Docker cases** (container per case, `docs/docker-cases.md`), or run separate Codeman instances per user (`CODEMAN_INSTANCE`, separate OS accounts). True per-user OS isolation is explicitly **out of scope** for this feature.
+- Partial mitigation at the agent layer: non-admin users default to Claude's `auto` permission mode (section 6.3), whose safety classifier blocks destructive actions and credential exfiltration. That reduces, but does not eliminate, cross-user snooping; the `canBypassPermissions` grant reopens it and should be given deliberately.
+
+This must be stated loudly in `docs/security-architecture.md`, the README section, and the admin panel UI ("Users share the host account; this separates workspaces, it does not sandbox users from each other").
+
+Also note the flip side: multi-user mode strictly _improves_ today's network posture, because it removes the single shared password and gives every person their own revocable credential.
+
+## 3. Activation and Mode Rules
+
+| Condition                                                     | Behavior                                                                                                                                                                                                                                                                   |
+| ------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| No flag (default)                                             | Exactly today's behavior. `users.json` is never read. Single-user auth via `CODEMAN_PASSWORD` if set.                                                                                                                                                                      |
+| `--multiuser` / `CODEMAN_MULTIUSER=1`, `users.json` has users | Multi-user auth active. `CODEMAN_PASSWORD` is ignored for login (warn if set).                                                                                                                                                                                             |
+| `--multiuser`, no `users.json` (first boot)                   | Bootstrap: if `CODEMAN_USERNAME`/`CODEMAN_PASSWORD` are set, create that user as the initial admin and continue. Otherwise refuse to start with instructions to run `codeman users add <name> --admin`. Never start multi-user with zero users (there would be no way in). |
+| `--multiuser` on a non-loopback bind                          | Allowed without `CODEMAN_PASSWORD`: `server.ts start()` treats "multi-user with >= 1 enabled user" as satisfying the auth requirement in the loud-warning check (wire into the existing `isLoopbackBindHost()` branch).                                                    |
+| Flag later removed                                            | Single-user mode again. Sessions/state that carry `owner` fields keep working (owner is simply ignored); user spaces remain on disk untouched.                                                                                                                             |
+
+Plumbing: flag in `src/cli.ts` (web command), env in a new `src/config/multiuser.ts` exporting `isMultiUserMode()`. Per-instance like everything else: a beta instance (`CODEMAN_INSTANCE=beta`) has its own `users.json` via `dataPath()`.
+
+## 4. Data Model and Disk Layout
+
+### 4.1 `~/.codeman/users.json` (via `dataPath('users.json')`, mode 0600, atomic write: tmp + rename)
+
+```jsonc
+{
+  "version": 1,
+  "users": [
+    {
+      "username": "alice", // canonical lowercase slug
+      "role": "admin", // "admin" | "user"
+      "password": {
+        "algo": "scrypt", // node:crypto scrypt, no new deps
+        "N": 16384,
+        "r": 8,
+        "p": 1,
+        "salt": "<hex 32B>",
+        "hash": "<hex 64B>",
+      },
+      "disabled": false,
+      "mustChangePassword": false, // set by admin reset; gates all API access until changed
+      "canBypassPermissions": false, // permission-mode grant, see section 6.3; false for new users
+      "createdAt": 1752900000000,
+      "lastLoginAt": 1752900000000,
+    },
+  ],
+}
+```
+
+- **Username rules**: `^[a-z0-9][a-z0-9_-]{1,31}$` (it becomes a folder name), stored lowercase, unique case-insensitively. Reserve `admin`? No: any name can be admin; role is a field, not a name.
+- **Hashing**: `scrypt` from `node:crypto` with per-user salt, compared via `timingSafeEqual`. Params stored per record so they can be raised later; verify tolerates old params and rehashes on next successful login.
+- New module `src/user-store.ts` (mirrors the `remote-hosts.ts` / `docker-hosts.ts` pattern): `readUsers()`, `writeUsers()`, `verifyPassword()`, `createUser()`, `setPassword()`, `deleteUser()`, plus pure helpers (`isValidUsername`, `hashPassword`) that are unit-testable without IO. In-process cache with short TTL like `readSettings`, invalidated on every write; the short TTL also covers the CLI (section 10) editing `users.json` while the server runs (cross-process changes picked up within the TTL).
+
+### 4.2 User spaces
+
+```
+~/codeman-users/
+  alice/
+    cases/
+      my-project/          <- same layout as today's ~/codeman-cases/<case>
+  bob/
+    cases/
+```
+
+- New helper in `route-helpers.ts`:
+  `resolveCasesDir(user?: AuthUser): string`
+  single-user mode: returns `CASES_DIR` (today's `~/codeman-cases`); multi-user: returns `join(USER_SPACES_DIR, user.username, 'cases')`, creating it lazily on first use.
+- `CASES_DIR` stays exported for single-user code paths, but every route usage (see 6) switches to the resolver.
+- The **user folder** (`~/codeman-users/<username>/`) is the deletion unit for "delete user + space" and leaves room for future per-user extras (uploads, exports) beside `cases/`.
+- Legacy `~/codeman-cases` in multi-user mode: surfaces to admins only, as a read-only "Unassigned (legacy)" group in the case list, with an admin action `POST /api/admin/cases/assign { case, username }` that `fs.rename`s the folder into a user's space (same-filesystem move, cheap). No automatic migration.
+
+## 5. Auth Pipeline Changes (`src/web/middleware/auth.ts`)
+
+Keep the existing single-user branch untouched. Add a parallel multi-user branch selected once at registration time:
+
+1. **Credential check**: Basic header parsed into `username:password`, verified against the user store (scrypt + `timingSafeEqual`). Disabled users fail closed.
+2. **Cookie sessions**: same `codeman_session` cookie and `StaleExpirationMap`, but `AuthSessionRecord` gains `username` and `role`. All existing TTL/sliding/eviction logic reused. Eviction cap becomes per-user aware (evict oldest _of that user_ first) so one user cannot flush everyone's sessions by logging in 100 times.
+3. **Request identity**: decorate `req.authUser = { username, role }` (Fastify decorateRequest). In single-user mode `req.authUser` is `{ username: 'admin', role: 'admin' }` when auth is on, and a synthetic admin when auth is off, so downstream code has ONE code path.
+4. **Rate limiting**: keep the per-IP bucket; add a per-username failure bucket (same `StaleExpirationMap` pattern) so a botnet cannot brute-force one account across IPs, and one flaky user behind a NAT cannot lock out the rest.
+5. **`mustChangePassword` gate**: when set, every API request except `GET /api/me`, `POST /api/me/password`, and static assets returns 403 with `errorCode: 'PASSWORD_CHANGE_REQUIRED'`; the frontend intercepts that code and shows the change-password modal.
+6. **Password change vs Basic-auth caching**: browsers cache Basic credentials. After a password change we revoke all of that user's cookie sessions; the next request falls to Basic with stale creds, gets 401, and the browser re-prompts. Acceptable for v1; a proper login form is Phase 6 (see 15).
+7. **Unchanged**: hook-secret loopback bypass (hooks authenticate the _instance_, not a user; the event maps to a session which has an owner), host guard, Origin/CSRF guard, security headers.
+8. **WS upgrade identity** (`ws-routes.ts`): the global auth `onRequest` hook does run on the upgrade request (`@fastify/websocket` v11 runs hooks before the handshake; browsers send the session cookie), but the route handler itself only checks Host/Origin and never learns WHO authenticated. Multi-user: the handler reads the decorated `req.authUser` and closes 4003 unless owner or admin (section 6.4; identity plumbing lands in Phase 2, the owner check in Phase 4 once sessions have owners). Add a regression test that an upgrade with no credentials is rejected while auth is active: the handler-level Host/Origin gate alone must never be mistaken for auth.
+9. **QR auth** (`/q/:code` redemption in `system-routes.ts`, minting in `tunnel-manager.ts`): today there is ONE global token, auto-rotated every 60s with a 90s grace window. A globally-rotating token cannot carry an identity (every logged-in user sees the same code), so multi-user mode replaces rotation with **on-demand minting**: an authenticated `POST /api/tunnel/qr` mints a single-use, short-TTL token bound to `req.authUser.username` (field on `QrTokenRecord`); redemption creates a cookie session for that user. Existing rate-limit buckets (`qrAuthFailures`, global `QR_RATE_LIMIT_MAX`) apply unchanged. Single-user mode keeps the rotating token.
+
+New error codes in `src/types/api.ts`: `FORBIDDEN`, `PASSWORD_CHANGE_REQUIRED`, `USER_EXISTS`, `USER_NOT_FOUND`, `LAST_ADMIN`.
+
+Role guard helper in `route-helpers.ts`: `requireAdmin(req, reply): boolean` used as the first line of every admin handler (403 `FORBIDDEN`), plus `requireOwnerOrAdmin(req, session)`.
+
+## 6. Ownership Threading (the big refactor)
+
+### 6.1 Sessions
+
+- `Session` gains `owner?: string` (constructor option), persisted in `SessionState.owner`, included in `toState()`, round-tripped through recovery (`mux-sessions.json` entries carry it, `restoreMuxSessions` passes it back, exactly like `remote`/`docker`).
+- Every session-creating path stamps the owner from `req.authUser`. Verified inventory of `new Session(...)` call sites: `POST /api/sessions` (session-routes.ts:444), `POST /api/quick-start` (:1956), `POST /api/run` one-shot (:1652), Ralph start (ralph-routes.ts:327), **cron** (cron-service.ts:352; `CronJob` gains `owner`, stamped at job create, launched as the job's owner), legacy `ScheduledRun` loop (server.ts:1603), plan generation + plan-orchestrator agents (plan-routes.ts:128, plan-orchestrator.ts:422/578; owner = requesting user), and recovery (server.ts:2225, next bullet). Two non-paths, also verified: **respawn never constructs a new Session** (it re-spawns the PTY on the same object, so `owner` survives automatically; no inheritance logic needed), and **orchestrator-loop creates no sessions** (it schedules work onto existing idle sessions via the task queue; its scoping requirement is different: it must only pick idle sessions owned by the goal's creator).
+- Recovery: `owner` must ALSO be mirrored on `MuxSession` (mux-sessions.json) and read back mux-first like `remote`/`docker` (`muxSession.owner ?? savedState?.owner`, the server.ts:2246-2250 pattern), or a reboot erases ownership on the next persist.
+- Every session-reading/mutating route filters: non-admin users only see and act on `session.owner === req.authUser.username`. Centralize in `findSessionOrFail` (route-helpers.ts:87; the owner check there covers the 6 route files that use it: system/session/respawn/ralph/file/plan-routes) and in the list endpoints (`GET /api/sessions`, `GET /api/sessions/unified`, `GET /api/status`). The Phase 3 audit must grep for BOTH `sessionManager.getSession` AND direct map access (`ctx.sessions.get(` / `.has(`): ws-routes and hook-event-routes reach sessions that way and bypass `findSessionOrFail`.
+- Admins see everything; every session row carries `owner` so the UI can badge it.
+
+### 6.2 Cases
+
+- All `CASES_DIR` call sites switch to `resolveCasesDir(req.authUser)`: `case-routes.ts` (list/create/delete/CLAUDE.md scaffolding, name-collision checks, docker quickcreate), `session-routes.ts` (quick-start case resolution, the workingDir-inside-cases env-strip check), `ralph-routes.ts` (case path resolution), and `plan-routes.ts:231` (easy to miss). Case-name-to-path resolution is currently DUPLICATED (`resolveCasePath` in case-routes.ts:82 and an inline copy in quick-start, session-routes.ts:1846-1863); consolidate into one owner-aware resolver as part of this refactor instead of patching both copies.
+- Registries that map case names to metadata become owner-scoped. `remote-cases.json`/`docker-cases.json` are arrays of objects, so entries simply gain `owner?: string` (absent = legacy: admin-only). `linked-cases.json` is a flat `Record<caseName, path>` with no room for a field: it needs a v2 shape (`{ "version": 2, "cases": { "<name>": { "path": "...", "owner": "..." } } }`) with read-time migration of the v1 form; it is read in two places (case-routes AND inline in quick-start), both must move to the new reader. Case names only need to be unique per user.
+- **Remote hosts and Docker hosts are machine-level resources**: CRUD on `/api/docker-hosts` and remote-host endpoints becomes admin-only in multi-user mode; regular users can _use_ hosts on their own cases but not define them. (Docker containers exec as the host account; letting any user define arbitrary `docker run` args is admin-equivalent.)
+- Case deletion, exports (`docker-exports/`), and imports check ownership; export filenames get an owner prefix to avoid collisions (fits the existing `^[a-zA-Z0-9._-]+\.tgz$` download guard).
+- **Workspace confinement for non-admins (the linchpin, do not skip)**: today `POST /api/sessions` accepts ANY host directory as `workingDir` (the only check is `statSync().isDirectory()`, session-routes.ts:305-318), and file-routes/attachments confine reads to `session.workingDir`. Without a new rule the whole scoping story is circular: a user points a session at `~/codeman-users/bob` (or `/home`) and the web layer itself serves that subtree, no agent needed. Rule: in multi-user mode a non-admin's `workingDir` must realpath-resolve inside their own space, enforced at `POST /api/sessions`, `POST /api/run`, cron job create AND fire time (the dir can change owners between the two), and Ralph auto-configure. Admins are unrestricted. This one rule is what makes the section 6.4 file-route line ("own space or own sessions' workingDirs") meaningful.
+
+### 6.3 Per-user Claude permission-mode policy
+
+Codeman now ships a global **Startup Mode** picker (App Settings, Claude CLI tab: `settings.claudeMode`, values `dangerously-skip-permissions` (default) | `auto` | `normal` | `allowedTools`; `auto` emits `--permission-mode auto`, Anthropic's classifier-guarded low-prompt mode). Multi-user mode layers a per-user policy on top of it:
+
+- **Default for regular users: `auto` only.** A non-admin's Claude sessions are forced to `--permission-mode auto` regardless of the global `claudeMode` setting. `normal` and `allowedTools` are also permitted (they are strictly more restrictive than auto), but `dangerously-skip-permissions` is NOT.
+- **Bypass is an explicit admin grant**: `canBypassPermissions: true` on the user record (default `false`, section 4.1). Only with that grant does the global skip-permissions default (or a future per-user choice) apply to their sessions.
+- **Admins** are unrestricted; the global setting applies to them as-is.
+- **Single enforcement point**: a pure `resolveClaudeModeForUser(globalMode, user)` in `user-store.ts`, applied server-side at option-resolution time, BEFORE the Session constructor, so both downstream arg builders inherit it for free (`buildPermissionArgs` in session-cli-builder.ts for the direct-PTY path AND `buildClaudePermissionFlags` in tmux-manager.ts for tmux panes; there are two builders, not one). Call sites where `getClaudeModeConfig()` feeds a spawn: session-routes.ts:452/1964, ralph-routes.ts:334, cron-service.ts:360, and recovery (server.ts:2214/2233). Recovery re-reads the GLOBAL setting on reboot, so the resolver must run there with the RECOVERED owner, or a restart silently un-downgrades every restored session. Never resolved in the frontend, so it cannot be bypassed via payload.
+- **Downgrade, don't error**: a non-granted user whose effective mode would be bypass gets `auto` silently (logged + surfaced as a badge on the session), so shared presets keep working.
+- **Other CLIs' bypass equivalents** follow the same grant: Codex `--dangerously-bypass-approvals-and-sandbox` (`codexDangerouslyBypassApprovals`) and Gemini `--approval-mode yolo` are refused for non-granted users (Gemini falls back to `auto_edit`, Codex to its default sandbox). Whether this stays one grant or splits per-CLI is an open question (section 15).
+- **Shell mode and custom launch commands follow the grant too**: `mode: 'shell'` sessions and cron `launchCommand` are arbitrary command execution as the host account, strictly stronger than any bypass flag, and no permission-mode downgrade applies to them. Non-granted users get 403 `FORBIDDEN` on shell session/quick-start creation and on cron jobs carrying `launchCommand` (checked at create AND at fire time). Folding them under `canBypassPermissions` keeps the model one-bit; section 15 asks whether it should split.
+- **Admin UI**: a "Can skip permissions" toggle per user in the Users tab (PATCH field, section 8), with a warning echoing the section 2 threat model.
+- Revoking the grant takes effect on the user's NEXT session start; live sessions are listed so the admin can restart them.
+
+### 6.4 Everything else that lists or streams
+
+| Surface                                                                    | Scoping rule                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+| -------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| SSE `/api/events`                                                          | Per-connection filter (see 7)                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| WS terminal (`ws-routes.ts`)                                               | Handler reads `req.authUser` (section 5.8) and closes 4003 unless owner or admin; today it checks Host/Origin only and has no identity                                                                                                                                                                                                                                                                                                                    |
+| `GET /api/search`                                                          | `harvestSources()` only over owned sessions                                                                                                                                                                                                                                                                                                                                                                                                               |
+| `GET /api/away-digest`                                                     | Aggregate only owned sessions/events                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| `GET /api/subagents`, workflow runs                                        | Filter by owning session (`claudeSessionId -> session -> owner`); agents not attributable to any session: admin-only                                                                                                                                                                                                                                                                                                                                      |
+| Push (`push-routes.ts`)                                                    | Subscription records currently carry NO identity (keyed by endpoint only): `subscribe` stamps `username`. All 8 `PUSH_EVENT_MAP` events are session-scoped, so routing = resolve owner from `data.sessionId`, deliver to that owner's (plus admins') subscriptions. Legacy identity-less subscriptions: admin-only delivery                                                                                                                               |
+| Screenshots `/api/screenshots`                                             | Per-user subdir `~/.codeman/screenshots/<username>/` in multi-user mode. Note: `GET /:name` deliberately rejects `/` in names as traversal, so derive the subdir server-side from `req.authUser` and keep client-visible names flat                                                                                                                                                                                                                       |
+| Attachments                                                                | Already session-scoped; inherits the session owner check. `attachmentConfineToWorkspace` is a global, default-OFF setting today: in multi-user mode it is FORCED ON for non-admins regardless of the setting (their attachments must resolve inside their own space); the setting keeps meaning what it means for admins                                                                                                                                  |
+| File routes (browse/preview)                                               | Path allowlist adds: non-admin paths must resolve (realpath) inside their own space or their own sessions' workingDirs                                                                                                                                                                                                                                                                                                                                    |
+| Settings (`settings.json`)                                                 | Global, admin-only writes in multi-user mode; reads allowed (per-device display keys stay in localStorage as today). Per-user server settings: out of scope v1                                                                                                                                                                                                                                                                                            |
+| System ops (self-update, tunnel toggle, span-displays, docker image build) | Admin-only                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| `getLightState` init snapshot                                              | Filtered per connection. Actual contents to filter (verified): `sessions`, `scheduledRuns`, `respawnStatus`, `subagents`, `workflowRuns`, `planUsage` (host-plan telemetry: admin-only); `globalStats` stays coarse-global. Cron jobs are NOT in the snapshot (they have their own REST route; filter there). The snapshot is cached process-wide (`LIGHT_STATE_CACHE_TTL_MS`): either key the cache per role/user or filter AFTER the cache on each send |
+
+## 7. SSE Event Filtering
+
+`/api/events` currently broadcasts everything to everyone. Ground truth first (verified): `broadcast()` lives in `SseStreamManager` (`sse-stream-manager.ts`), not server.ts; clients are keyed by the raw Fastify reply (`sseClients: Map<FastifyReply, Set<string> | null>`, plus `sseClientsById` for live filter updates); the existing `?sessions=` filter is a bandwidth optimization applied ONLY to `session:terminal` batches in `flushSessionTerminalBatch()`, while `broadcast()` itself loops ALL clients unconditionally. The single-client delivery primitive already exists (`sendSSE`, used for the per-connection init snapshot). Plan:
+
+- At connection time, resolve `req.authUser` and store `{ username, role }` with the client. Concretely: extend `addClient(reply, sessionFilter, isRemote, clientId)` to take the identity and change the `sseClients` map value to `{ filter, identity }` (or add a parallel `Map<reply, identity>`); there is no per-client record object today to hang it on.
+- `broadcast()` gains an optional routing hint: `broadcast(event, data, { sessionId?, adminOnly?, username? })`. Resolution order per client: admin sees all; `username` targets one user; `sessionId` resolves owner via SessionManager; `adminOnly` for machine-level events (docker image builds, tunnel, self-update); no hint = broadcast to all (connection status etc.).
+- **Enforce the identity check in BOTH `broadcast()` AND `flushSessionTerminalBatch()`**: the terminal batch path does not go through `broadcast()`, and it carries the highest-value payload (raw terminal bytes).
+- Sweep of the ~120 backend event constants in `sse-events.ts`: mechanically, everything `session:*`, `ralph:*`, `respawn:*`, `subagent:*`, `workflow:*`, `attachment:*`, `cron:*` (job owner) carries or can resolve a sessionId/owner; `docker:*`, `system:*`, tunnel and update events are adminOnly; a short tail needs case-by-case decisions during implementation.
+- The existing `?sessions=` filter and `/api/events/subscribe` compose with (never override) the ownership filter: the subscription filter can only narrow within what the identity allows.
+
+## 8. Admin API (`src/web/routes/admin-routes.ts`, new module + `AdminPort`)
+
+All handlers: multi-user mode only (404 otherwise), `requireAdmin`, Zod schemas in `schemas.ts`, `ApiResponse` envelope, audit-logged.
+
+| Endpoint                                         | Behavior                                                                                                                                                                                                                                                                                                                                                                                                                |
+| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `GET /api/admin/users`                           | List users + stats: role, disabled, createdAt, lastLoginAt, live session count, case count, space disk usage (best-effort async walk, cached 60s), active cookie-session count                                                                                                                                                                                                                                          |
+| `POST /api/admin/users`                          | Create: `{ username, role, password? }`. No password given: generate a one-time password, return it ONCE in the response, set `mustChangePassword`                                                                                                                                                                                                                                                                      |
+| `PATCH /api/admin/users/:username`               | `{ role?, disabled?, canBypassPermissions? }`. Demoting/disabling the last enabled admin: 409 `LAST_ADMIN`. Disable also revokes cookie sessions. `canBypassPermissions` is the section 6.3 grant (default false)                                                                                                                                                                                                       |
+| `POST /api/admin/users/:username/reset-password` | Generates one-time password (returned once), sets `mustChangePassword`, revokes cookie sessions                                                                                                                                                                                                                                                                                                                         |
+| `POST /api/admin/users/:username/logout`         | Revoke all cookie sessions for that user. Honest limit under Basic auth: the browser silently re-sends cached credentials and gets a fresh cookie on the next request, so logout only truly ends QR-issued sessions; to actually lock someone out, disable the account or reset the password. Say so in the panel tooltip until Phase 6                                                                                 |
+| `DELETE /api/admin/users/:username`              | `{ deleteSpace?: boolean }` (default false). Refuses last admin. Kills the user's live sessions first (normal kill flow, incl. docker/remote teardown per case), revokes cookies, removes from store. With `deleteSpace`: guarded recursive delete of `~/codeman-users/<username>` (realpath must be inside `USER_SPACES_DIR`, top-level dir must not be a symlink), plus their registry entries and push subscriptions |
+| `POST /api/admin/cases/assign`                   | Move a legacy `~/codeman-cases/<case>` into a user's space (`fs.rename`)                                                                                                                                                                                                                                                                                                                                                |
+| Self-service `GET /api/me`                       | `{ username, role, mustChangePassword }` (works in single-user mode too: synthetic admin; the frontend uses it to decide whether to render admin UI)                                                                                                                                                                                                                                                                    |
+| Self-service `POST /api/me/password`             | `{ currentPassword, newPassword }`, verifies current, min length 8, revokes other sessions, clears `mustChangePassword`                                                                                                                                                                                                                                                                                                 |
+
+**Audit log**: append-only `~/.codeman/admin-audit.jsonl` (same idiom as `session-lifecycle.jsonl`): timestamp, acting admin, action, target, request IP. User management without an audit trail is not acceptable even for a homelab tool.
+
+SSE additions (both `sse-events.ts` and `constants.js`): `admin:usersChanged` (adminOnly; the panel re-fetches) and `auth:passwordChangeRequired` (targeted to the user).
+
+## 9. Frontend
+
+- **`GET /api/me` on boot** (app.js init): stores `window.__codemanUser`; everything below keys off it. Single-user mode returns the synthetic admin, so the UI needs no mode awareness beyond "am I admin".
+- **Admin panel**: new tab "Users" in the App Settings modal (settings-ui.js), rendered only for admins in multi-user mode. Table of users with actions (create, reset password showing the one-time password in a copy-to-clipboard reveal, enable/disable, role toggle, logout, delete with a typed-username confirm for the delete-space variant). No new header button (mobile header policy test stays green; the settings modal is already reachable everywhere).
+- **Change-password modal**: shown on `PASSWORD_CHANGE_REQUIRED` (fetch interceptor in api-client.js) and reachable from settings for self-service.
+- **Owner badges**: admin's session tabs and the session palette/manager show `owner` on foreign sessions; regular users see no change.
+- New module `admin-ui.js` if the settings-ui.js addition gets large (load order after settings-ui, before session-ui), else keep inside settings-ui.js. Follow the `@fileoverview` + `@loadorder` convention either way.
+
+## 10. CLI Additions (`src/cli.ts`)
+
+Headless bootstrap and recovery must not require the web UI:
+
+```
+codeman users add <name> [--admin]     # prompts for password (hidden input), or --password-stdin
+codeman users passwd <name>            # reset password
+codeman users list
+codeman users rm <name> [--delete-space]
+```
+
+These operate directly on `users.json` via `user-store.ts` (no server needed), honoring `CODEMAN_INSTANCE`. This is also the answer to "locked out: last admin forgot password".
+
+## 11. Limits and Config
+
+- New `src/config/multiuser.ts`: `isMultiUserMode()`, `USER_SPACES_DIR` (`~/codeman-users`, overridable via `CODEMAN_USER_SPACES_DIR` for tests), `MAX_USERS` (default 25), per-user session cap (default: global cap / 2, env `CODEMAN_MAX_SESSIONS_PER_USER`).
+- Cap enforcement is currently COPY-PASTED: the global `MAX_CONCURRENT_SESSIONS` (50, `config/map-limits.ts:25`) check appears at 6 independent sites (session-routes.ts:298/1622/1683, ralph-routes.ts:275, cron-service.ts:340, server.ts:1595). Do not add a 7th copy per site: extract one `assertSessionCapacity(ctx, owner?)` helper doing the global + per-user checks and use it everywhere, or the per-user cap WILL miss a path.
+- Global limits (50 sessions, SSE clients 100, terminal buffers) are unchanged and shared; the per-user session cap is the fairness lever.
+
+## 12. Compatibility Matrix
+
+| Concern            | Guarantee                                                                                                                                                                                                   |
+| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Default (no flag)  | No behavior change. No new file reads on the hot path. All new fields optional in state                                                                                                                     |
+| State round-trip   | `SessionState.owner`, `MuxSession.owner`, `CronJob.owner`, registry `owner` fields are optional; old state loads clean; new state loaded by an old build ignores unknown fields (existing tolerant parsing) |
+| Instance isolation | `users.json`, audit log, screenshots subdirs all via `dataPath()`; user spaces dir is shared across instances like `~/codeman-cases` is today (documented)                                                  |
+| API versioning     | HTTP API is internal per `docs/versioning-policy.md`; still, all changes are additive. Ship as a **minor** version                                                                                          |
+| Hooks              | Unchanged (instance-level hook secret; owner resolved from the session)                                                                                                                                     |
+
+## 13. Implementation Phases
+
+Each phase is independently shippable behind the flag and ends with its tests green.
+
+**Phase 1: user store + mode plumbing** (no behavior change yet)
+`src/user-store.ts`, `src/config/multiuser.ts`, CLI `users` subcommands, bootstrap-on-first-boot logic, `users.json` schema + atomic writes.
+Tests: `test/user-store.test.ts` (hashing, verify, params upgrade, username validation, atomic write, last-admin invariants; pure, no server).
+
+**Phase 2: multi-user auth**
+Auth middleware branch, `req.authUser` decoration, cookie records with username/role, per-username rate bucket, `mustChangePassword` gate, WS upgrade identity plumbing + unauthenticated-upgrade regression test (section 5.8), QR on-demand minting + identity binding (section 5.9), `GET /api/me`, `POST /api/me/password`, error codes, network-bind check integration.
+Tests: `test/multiuser-auth.test.ts` (live server, unique port 3170+; wrong password, disabled user, cookie carries identity, per-user rate limit isolation, mustChangePassword lockbox, QR redemption identity). Reuse the `delete process.env.CODEMAN_PASSWORD` idiom from `test/setup.ts`.
+
+**Phase 3: ownership threading**
+Session `owner` + persistence + `MuxSession` mirror + recovery; `resolveCasesDir()` refactor across case/session/ralph/plan routes (consolidating the duplicated case-path resolution); registry owner fields incl. the linked-cases v2 shape; `findSessionOrFail` owner check + the direct-`sessions.get` audit; list filtering; owner stamping across ALL create paths from 6.1; **non-admin workingDir confinement** (6.2); permission-mode/shell/launchCommand policy (6.3); `assertSessionCapacity` helper + per-user cap.
+Tests: `test/routes/ownership-scoping.test.ts` (inject-based: user A cannot read/kill/input user B's session, case lists are disjoint, admin sees both), extend `test/cron-service.test.ts` for owner stamping, recovery round-trip in the existing mux-recovery tests.
+
+**Phase 4: event fan-out + remaining surfaces**
+SSE routing hints + client identity (enforced in BOTH `broadcast()` and the terminal-batch flush), WS owner gate (identity landed in Phase 2), search/digest/subagent/workflow scoping, push subscription identity + owner routing, screenshot subdirs, file-route scoping, `getLightState` filtering + per-identity caching, admin-only system ops.
+Tests: `test/sse-ownership.test.ts` (two SSE clients, event for A's session reaches only A + admin), WS upgrade rejection test, search/digest scoping tests.
+
+**Phase 5: admin API + frontend**
+`admin-routes.ts` + `AdminPort` + schemas + audit log + `admin:usersChanged`; settings-ui Users tab, change-password modal, owner badges, api-client interceptor.
+Tests: `test/routes/admin-routes.test.ts` (CRUD, last-admin 409, one-time password flow, delete-space guard rails incl. symlink refusal), frontend vm-sandbox test following `test/run-mode-ui.test.ts` pattern, Playwright pass per the always-end-to-end rule before calling it done.
+
+**Phase 6 (optional, later): login page**
+Replace Basic with a form + `POST /api/login` in multi-user mode only (fixes browser credential caching UX, enables logout button). Explicitly deferred; Basic works for v1.
+
+**Docs**: update `docs/security-architecture.md` (new section: multi-user model + threat model from section 2), `README.md` (short opt-in section), `CLAUDE.md` (Key Patterns entry + State Files + route/SSE counts), this file gets a "shipped" status stamp per phase.
+
+## 14. Key Risks / Decisions Made
+
+1. **Not a security boundary at the agent layer** (section 2). Decided: ship with loud documentation; Docker cases are the isolation story.
+2. **`findSessionOrFail` as the single enforcement point** for ~30 session routes: any route that fetches sessions another way must be audited in Phase 3 (grep for `sessionManager.getSession` outside route-helpers).
+3. **SSE sweep is the riskiest surface**: a missed event leaks metadata (not terminal content, which is session-scoped, but names/paths). Phase 4 includes a checklist pass over all ~138 events with the default flipped to "owner-scoped unless explicitly global": fail closed.
+4. **Basic-auth password-change UX** is mediocre (browser re-prompt). Accepted for v1; Phase 6 fixes it properly.
+5. **Legacy case migration** is manual (admin assigns). No silent moves of user data.
+6. **Case-name uniqueness becomes per-user**; tmux session names already include the session id so no collision, but the `w<n>-<case>` tab naming and lifecycle-log rows should include the owner for disambiguation in admin views.
+7. **`workingDir` confinement (6.2) is the single most load-bearing rule**: every file-serving and agent-spawning surface downstream trusts `session.workingDir`. Review and test it as carefully as the auth branch (foreign-space path, symlink into a foreign space, `..` traversal, cron fire-time re-check).
+8. **The WS handler never sees identity today** (auth happens only in the global hook): the 5.8 wiring is new code on a security-sensitive path; cover unauthenticated, foreign-user, and admin upgrades with tests.
+
+## 15. Open Questions (answer before Phase 3)
+
+1. Should admins' own cases live in `~/codeman-users/<admin>/cases` (symmetric, proposed) or keep using legacy `~/codeman-cases`? Proposed: symmetric; legacy dir is a migration source only.
+2. Per-user settings (respawn presets, notification prefs): global-only in v1. Worth a `users/<name>/settings.json` overlay later?
+3. Should regular users be allowed to create Docker cases on admin-defined hosts (proposed: yes) or is Docker entirely admin-only?
+4. Session handoff: does an admin need "reassign session/case to another user"? (Cheap to add next to `cases/assign`; not in v1 scope.)
+5. Permission-mode grants (section 6.3): one `canBypassPermissions` flag covering Claude/Codex/Gemini bypass equivalents PLUS shell mode and cron `launchCommand` (proposed: one flag, keep it one-bit), or split into `canBypassPermissions` + `canRunArbitraryCommands`? And should admins be able to set a per-user DEFAULT mode (for example force `normal` for an intern) rather than just gating bypass?
+6. OpenCode has no single bypass flag (its permission config rides `OPENCODE_CONFIG_CONTENT`): decide what the grant means there before Phase 3, or exclude OpenCode mode for non-granted users in v1.

docs/remote-sessions.md

@@ -0,0 +1,246 @@
+# Remote Sessions (SSH)
+
+Codeman can run a session's agent on a **remote host over SSH** instead of the
+local machine. The agent (Claude, OpenCode, Codex, Gemini, or a plain shell)
+runs inside a `tmux` server **on the remote host**, so it survives the SSH
+connection dropping; Codeman attaches to it the same way it attaches to a local
+managed session.
+
+This document covers the data model, the shell-safe SSH command construction
+(COD-107), the durable-launch design (COD-104), and the operational caveats.
+For the local session/mux machinery this builds on, see the **Mux** and
+**Session** entries in `CLAUDE.md` → Architecture.
+
+## Why it exists
+
+A developer box (`AA-DESKTOP`) often needs to drive an agent on another machine —
+a NAS, a build server, a host reachable only through a jump box or a
+cloudflared SOCKS5 proxy. Rather than wrap `ssh` by hand per host, Codeman
+stores reusable **remote hosts** + **remote cases** and reproduces the exact
+connection the operator already uses (`ssh-aa-desktop`-style configs:
+custom port, identity file, `-J` jump host, `-o ProxyCommand`).
+
+## Data model
+
+Types live in `src/types/session.ts`; persistence in `src/remote-hosts.ts`.
+
+| Type | Role |
+|------|------|
+| `RemoteSshOptions` | The **HOW-to-reach** fields, shared by host + session: `identityFile`, `socksProxy` (`host:port`), `jumpHost` (`[user@]host[:port]`), `extraSshOptions` (`KEY=VALUE[]`). Every field optional — all-absent reproduces port-22, default-identity, directly-SSH-able behavior. |
+| `RemoteHost` (extends `RemoteSshOptions`) | A saved host: `id`, `label`, `host`, `username`, `port?`, `commands?` (per-mode launch command override). |
+| `RemoteCase` | A working directory on a host: `name`, `type: 'remote'`, `hostId`, `remotePath`. |
+| `SessionRemote` (extends `RemoteSshOptions`) | The resolved bundle stamped onto a live session: host coordinates + `remotePath` + `commands`, plus **`owned?`** and **`remoteSessionName?`** (COD-105 — see [Ownership](#ownership-launched-vs-discovered-and-attached-cod-105)). Built by `toSessionRemote(host, case)` (sets `owned: true`) for the launch path, or `toAttachedSessionRemote(host, name, path)` (sets `owned: false`) for the attach path. Both copy the advanced SSH options through so every connection is identical. |
+| `RemoteCommandMode` | `Extract<SessionMode, 'shell' \| 'claude' \| 'opencode' \| 'codex' \| 'gemini'>` — the modes that can run remotely. |
+| `RemoteSessionInfo` (COD-105) | One discovered remote tmux session: `name` (always `codeman-*`), `attached` (a client is connected), `created` (epoch s), `windows`. Returned by `listRemoteCodemanSessions()`. |
+
+Persistence is two flat JSON arrays in the instance data dir:
+
+- `~/.codeman/remote-hosts.json` — `readRemoteHosts()` / `writeRemoteHosts()`
+- `~/.codeman/remote-cases.json` — `readRemoteCases()` / `writeRemoteCases()`
+
+(Paths via `remoteHostsPath()` / `remoteCasesPath()`; both honor `CODEMAN_INSTANCE`
+because the config dir is the instance data dir.)
+
+On the live `Session`, the remote rides as `_remote?: SessionRemote`. When
+attaching, `resolveMuxAttachCwd()` forces the cwd to `/tmp` for remote sessions —
+the local working directory is meaningless on the remote box.
+
+## SSH command construction (COD-107 — the injection surface)
+
+**All** SSH command lines flow through one function so user-controlled fields are
+escaped once and the launch + prereq probe can never drift apart:
+
+```ts
+// src/remote-hosts.ts
+buildSshConnectionArgs(remote: RemoteSshOptions & Pick<RemoteHost, 'port'>): string[]
+```
+
+It returns the **ordered leading tokens** of an ssh command line (no `-t`, no
+target, no remote command):
+
+```
+ssh -o BatchMode=yes
+    [-p <port>]
+    [-i <abs-identity>]            # ~ / $HOME expanded, then shellescaped
+    [-J <jumpHost>]                # shellescaped, single token
+    [-o ProxyCommand=nc -X 5 -x <socks> %h %p]   # ONE shellescaped -o token
+    [-o <KEY=VALUE>] …             # each extra option, shellescaped
+```
+
+Rules that keep this safe — **do not bypass them by hand-building an ssh line elsewhere:**
+
+- **Every** user-controlled value (`-i`, `-J`, `-o`, ProxyCommand) is POSIX
+  single-quote `shellescape`d (`'…'` with embedded `'\''`). The helper mirrors
+  the one in `tmux-manager.ts`.
+- **`~`/`$HOME` in `identityFile` is expanded at build time** (`expandIdentityPath`),
+  *before* escaping — ssh does not expand `~` inside `-i`, and the escaped value
+  never reaches a shell that would.
+- **The ProxyCommand is one shellescaped `-o KEY=VALUE` token**, so its spaces and
+  the `%h`/`%p` placeholders reach ssh as a single argument. `%h %p` survive
+  verbatim — **ssh** expands them to the real host/port, not the shell.
+- **Empty options ⇒ `['ssh', '-o BatchMode=yes']`** (+ `-p` only when set) —
+  byte-identical to the historical behavior.
+
+Token construction is unit-tested independently of any live connection (see
+`test/` for `buildSshConnectionArgs` / `buildRemoteTmuxCheckCommand` cases).
+
+## Durable launch (COD-104)
+
+`buildRemoteLaunchCommand({ mode, remote, sessionId })` in `tmux-manager.ts`
+builds the command that launches (or **reattaches** to) the remote session:
+
+```
+ssh -o BatchMode=yes -t <connection-args> user@host \
+  'tmux -L codeman-remote new-session -A -s codeman-ssh-<id8> -c <remotePath> "cd <remotePath> && exec <cli>" \; \
+     set -t codeman-ssh-<id8> status off \; set -t codeman-ssh-<id8> mouse off \; \
+     set -t codeman-ssh-<id8> prefix C-q \; set -s escape-time 0 \; \
+     set -t codeman-ssh-<id8> window-size latest'
+```
+
+Key points:
+
+- **`new-session -A -s codeman-ssh-<id8>`** = attach-if-exists-else-create, so a
+  reconnect (same deterministic `remoteTmuxSessionName(sessionId)` — `codeman-ssh-` +
+  the first 8 chars of the session id) lands back in
+  the **same** remote session rather than spawning a duplicate. This is what makes
+  the remote agent survive an SSH drop. The name deliberately fails
+  `SAFE_MUX_NAME_PATTERN` so a Codeman running ON the remote host never adopts it.
+- **`-L codeman-remote`** = a DEDICATED socket for sessions launched by remote
+  Codemans, NOT the canonical `-L codeman` socket the remote host's own Codeman
+  uses. Options are set per-session (`set -t`), never `-g`, so a shared remote
+  tmux server's other sessions are untouched (#145 hardening). Note the
+  asymmetry: **discovery/attach (COD-105) target the canonical `-L codeman`
+  socket** — they join sessions the remote's own Codeman manages, while owned
+  durable launches live on `-L codeman-remote`.
+- **`exec <cli>`** replaces the pane shell with the agent, so the pane PID *is*
+  the agent. The per-mode command comes from `remote.commands?.[mode]` or
+  `defaultRemoteCommandForMode(mode)` (`exec claude` / `exec opencode` /
+  `exec codex` / `exec gemini` / `exec bash -l`).
+- The **whole tmux invocation is a single shell-quoted ssh argument**, and the
+  pane command is independently quoted, so a `remotePath` with spaces is safe.
+- Connection options come from the **same `buildSshConnectionArgs(remote)`** as
+  the prereq probe; `-t` is inserted right after `ssh -o BatchMode=yes`,
+  preserving historical token order.
+
+### tmux prerequisite probe
+
+Because durable remote sessions require tmux on the remote host,
+`checkRemoteTmuxAvailable(host)` runs `command -v tmux` over SSH **before**
+creating a remote case/session and returns a structured, never-throwing result:
+
+- empty stdout / non-zero exit → *"remote host `<host>` needs tmux installed for
+  durable remote sessions"*
+- stderr present → *"could not verify tmux on remote host `<host>`: `<stderr>`"*
+  (a real connection failure, surfaced to the operator)
+- success → `{ ok: true, tmuxPath }`
+
+It connects with the **identical** options as the launch
+(`buildRemoteTmuxCheckCommand` reuses `buildSshConnectionArgs` and inserts
+`-o ConnectTimeout=10`), so a proxied/custom-port/identity host that the launch
+can reach also passes the probe (and vice-versa).
+
+**Test-mode short-circuit:** under `VITEST` the probe returns
+`{ ok: true, tmuxPath: '(test-mode)' }` without opening a socket — mirroring
+`TmuxManager`'s no-op-shell-under-VITEST (`IS_TEST_MODE`). Without it, remote-case
+create-path tests would hit a real ~10s ssh timeout. Only the live probe is
+skipped; command construction is still asserted by unit tests.
+
+## Ownership: launched vs. discovered-and-attached (COD-105)
+
+COD-104 (above) was Phase 1 — Codeman *launches* a remote session and owns it.
+COD-105 is Phase 2 — Codeman can also **discover** `codeman-*` tmux sessions
+already running on a remote host (created by the remote's own Codeman or another
+instance) and **attach** to one it didn't launch. Ownership decides what happens
+when the tab closes.
+
+`SessionRemote.owned` carries this:
+
+- **`owned: true`** (or absent — legacy/COD-104 sessions persisted before this
+  field) — we launched it via `buildRemoteLaunchCommand` and may explicitly kill it.
+- **`owned: false`** — discovered + attached; another Codeman owns the remote
+  session. `remoteSessionName` holds its existing tmux name. Closing the tab
+  **detaches**, never kills.
+
+### Discovery
+
+`listRemoteCodemanSessions(host)` lists the remote's `codeman-*` sessions:
+
+- `buildRemoteListSessionsCommand()` runs `tmux -L codeman list-sessions -F "…"`
+  over SSH (connection args from the shared `buildSshConnectionArgs`, so discovery
+  connects identically to launch/probe). `2>/dev/null` swallows tmux's "no server
+  running" stderr.
+- `parseRemoteSessionList()` is a **pure, unit-tested** parser. ⚠️ Quirk: the
+  remote tmux's `-F "…\t…"` format emits the **literal two-character `\t`**, not a
+  real tab (verified on tmux next-3.7), so the parser splits on `/\\t|\t/` (literal
+  backslash-t **or** a real tab, for builds that do expand it). It keeps only
+  `codeman-*` names, coerces types, and skips malformed lines.
+- `listRemoteCodemanSessions()` **never throws** — unreachable host / no tmux / no
+  sessions all map to `[]`. Like the prereq probe, it **no-ops to `[]` under
+  `VITEST`** so a request path never opens a real ssh connection.
+
+Discovery is **explicit** — the UI has a "Discover existing sessions" button per
+host; Codeman never auto-discovers on host select.
+
+### Attach vs. launch selection
+
+`buildRemoteSessionCommand(mode, remote, sessionId)` in `tmux-manager.ts` picks the
+remote command line by ownership:
+
+- **`owned === false`** → `buildRemoteAttachCommand(remote, name)` — emits
+  `ssh … -t … 'tmux -L codeman attach -t <remoteSessionName>'`. It uses **`attach`,
+  NOT `new-session -A`**, so it only *joins* an existing session and never creates
+  one.
+- **owned (default)** → `buildRemoteLaunchCommand` (the COD-104 path above).
+
+### Detach-not-kill
+
+`TmuxManager.killSession()` has an **early return for non-owned remote sessions**:
+it tears down **only the LOCAL pane** holding the ssh client (`tmux -L codeman
+kill-session` on *this* host's socket). Killing the local ssh sends SIGHUP to the
+remote `tmux attach`, which **detaches** — the durable remote session survives.
+The early return is a structural guarantee that **no code path can ever issue a
+remote `kill-session` for a session we don't own** — the only `kill-session` run is
+on the local socket, which never reaches the remote socket.
+
+## API
+
+Routes are registered in `src/web/routes/case-routes.ts`:
+
+| Method | Path | Purpose |
+|--------|------|---------|
+| `GET` | `/api/remote-hosts` | List saved hosts |
+| `POST` | `/api/remote-hosts` | Create a host |
+| `PUT` | `/api/remote-hosts/:id` | Update a host |
+| `DELETE` | `/api/remote-hosts/:id` | Delete a host |
+| `GET` | `/api/remote-hosts/:hostId/sessions` | Discover `codeman-*` sessions on the host (COD-105; `listRemoteCodemanSessions`, never errors) |
+| `POST` | `/api/cases/remote-link` | Link a case to a remote host (creates the `RemoteCase`) |
+
+Attaching to a discovered session is a **session-create** path, not a host route:
+`POST /api/sessions` accepts `attachRemoteSession: { hostId, remoteSessionName }`
+(schema in `schemas.ts`; `remoteSessionName` must match `^codeman-[a-zA-Z0-9._-]+$`),
+which `session-routes.ts` turns into a non-owned (`owned: false`) session.
+
+Frontend touchpoints: the remote-host management UI is in `session-ui.js` /
+`panels-ui.js`; a remote session is created by picking a remote host/case in the
+session-create flow, or via the per-host **"Discover existing sessions"** button →
+**Attach** action (creates an `owned: false` session).
+
+## Security notes
+
+- **`identityFile` is a path only — never key bytes.** Codeman stores the path and
+  passes it to `ssh -i`; the key never enters Codeman's state or the wire.
+- The injection surface is the SSH option fields. The single-source
+  `buildSshConnectionArgs` + `shellescape` discipline (COD-107) is the control —
+  audit any new code path that constructs an ssh command to route through it
+  rather than concatenating options inline.
+- `BatchMode=yes` means **no interactive password/passphrase prompts** — remote
+  hosts must be reachable with key-based or agent auth (or an unencrypted key the
+  agent has loaded). A host needing a passphrase will fail the probe with an ssh
+  diagnostic rather than hang.
+
+## Related
+
+- `CLAUDE.md` → Architecture → **Remote** row, and the **Remote sessions (SSH)**
+  Key Pattern.
+- `docs/security-architecture.md` — overall network/auth model.
+- COD-104 (tmux prereq + durable launch), COD-105 (discover + attach, detach-not-kill ownership), COD-107 (shell-safe connection args).

docs/security-architecture.md

@@ -30,7 +30,8 @@ an explicit, guided opt‑in.
 7. [Supply‑chain & build‑asset hardening](#7-supplychain--buildasset-hardening-cod28)
 8. [Multi‑instance isolation](#8-multiinstance-isolation)
 9. [Transport security headers](#9-transport-security-headers)
-10. [Quick reference](#10-quick-reference)
+10. [Docker container isolation](#10-docker-container-isolation)
+11. [Quick reference](#11-quick-reference)
 
 ---
 
@@ -248,16 +249,28 @@ Ordered most‑to‑least recommended:
 
 ### A. Tailscale serve (recommended)
 
-Bind loopback, let Tailscale front it on your tailnet with a real cert:
+Bind loopback, let Tailscale front it on your tailnet with a real cert. **The
+installer sets this up for you**: choose **Tailscale** at the network-access
+prompt, or retrofit an existing install with:
 
 ```bash
-codeman web --https            # binds 127.0.0.1:3000
-tailscale serve --bg https / http://127.0.0.1:3000
+bash ~/.codeman/app/install.sh tailscale
 ```
 
-Only devices on your tailnet can reach it; Tailscale handles identity. No app
-password and no `0.0.0.0` bind required. (This is the maintainer's production
-setup.)
+The guided flow installs Tailscale if needed, walks through login and the
+tailnet HTTPS-certificates toggle, and configures the equivalent of:
+
+```bash
+codeman web                    # binds 127.0.0.1:3000 (plain HTTP is fine here)
+tailscale serve --bg 3000      # HTTPS at https://<node>.<tailnet>.ts.net
+```
+
+Only devices on your tailnet can reach it; Tailscale handles identity and
+terminates TLS with a real Let's Encrypt certificate (so PWA install and web
+push work). No app password and no `0.0.0.0` bind required. (This is the
+maintainer's production setup.) `CODEMAN_TAILSCALE=1` presets the choice for
+automation; the installer never runs `tailscale serve reset` and never touches
+serve mappings other than `443 -> Codeman's port`.
 
 ### B. Authenticated cloudflared tunnel + password
 
@@ -471,7 +484,45 @@ production layout (`~/.codeman`, `-L codeman`, port 3000).
 
 ---
 
-## 10. Quick reference
+## 10. Docker container isolation
+
+Docker cases (1.4.0) run a session inside a per‑case container instead of on the host. The security posture:
+
+- **Hardened create flags, always** — `--cap-drop ALL`, `--security-opt no-new-privileges`, `--pids-limit` (fork‑bomb guard), `--memory` == `--memory-swap` (a real OOM cap), `--init`, and non‑root: `--user <hostUid>:0` on Linux (host uid → workspace files stay host‑owned; GID 0 keeps `$HOME` writable), `--userns=keep-id` on rootless Podman. **Never** `--privileged`, and **never** the docker socket — the pure builder in `docker-hosts.ts` cannot emit them and the schema cannot represent them.
+- **Credentials never enter an image** — the convenient default bind‑mounts host cred dirs (`~/.claude`, `~/.codex`, `~/.gemini`, `~/.config/{gcloud,opencode}`) read‑write. Bind mounts are physically excluded from `docker commit`, so exported images are secret‑free. API‑key CLIs get their key as an exec‑time NAME‑ONLY `--env OPENAI_API_KEY` (no `=value`, no `ps` leak, never committed); a create‑time `-e` for a secret is never used. The **sealed** profile (`mountCredentials:false` + `network:none`) drops the host mounts; full‑image export is then refused (an in‑container login would ride the committed layer) unless a pre‑commit scrub is opted into.
+- **Blast radius — accept it explicitly** — the convenient profile mounts an arbitrary host workspace RW plus the host credential dirs RW into a network‑enabled container, so container‑run agent code can read/modify those host trees and reach the network at once. Still a net improvement over today's on‑host `--dangerously-skip-permissions` execution; use the sealed profile for genuinely untrusted work.
+- **Import is untrusted‑bundle‑safe** — `/api/docker-cases/import` validates the manifest + per‑member SHA‑256 before extraction, rejects absolute / `..` tar members (traversal guard), and re‑tags the loaded image into a quarantined namespace so it can never overwrite `codeman/agent:base` or a pre‑existing tag.
+- **Host guard & the bridge‑hooks listener** — in‑container hook callbacks carry `Host: host.docker.internal` / `host.containers.internal`; both are on the always‑on host‑header allowlist (`DOCKER_HOST_GATEWAY_ALIASES`) and resolve to the host only from inside a container netns, so they are not a browser DNS‑rebinding surface. On a loopback‑only server, in‑container hooks are opt‑in via `CODEMAN_DOCKER_BRIDGE_HOOKS=1`, which binds a SECOND listener on the docker bridge gateway serving **only** the hook endpoints (every other path → `403`) into the same hook‑secret‑gated pipeline. The bridge is host‑internal (containers + host), not the LAN, so it does not widen network exposure; the hook secret is bind‑mounted read‑only and referenced by path.
+- **Instance isolation** — every managed container is labeled `codeman.instance=<CODEMAN_INSTANCE>`; the boot reaper reaps orphans of its OWN instance only, so a beta never removes a prod container. The in‑container tmux socket (`-L codeman-docker`) + session name (`codeman-dkr-*`) deliberately fail a nested Codeman's discovery pattern.
+
+Full feature guide: [`docker-cases.md`](docker-cases.md).
+
+---
+
+## 10a. Multi‑user mode (opt‑in)
+
+`codeman web --multiuser` (or `CODEMAN_MULTIUSER=1`) turns on named users with individually scrypt‑hashed passwords in `~/.codeman/users.json` (mode 0600). OFF by default; when off, nothing here applies and behavior is byte‑identical to single‑user. Design + phase status: [`multi-user-plan.md`](multi-user-plan.md).
+
+- **It is workspace separation, NOT a security boundary between users.** Every session still runs as the SAME OS account with agent code that can read the whole host. Any user can ask their agent to `cat` another user's files; the WEB layer enforces scoping, the AGENT layer cannot. Mitigations: give non‑admins the default `auto` permission mode (classifier‑guarded), pair users with **Docker cases** (container per case) for real isolation, or run separate Codeman instances under separate OS accounts. Stated loudly in the admin panel and the plan's threat model (section 2).
+- **It strictly improves network posture.** It removes the single shared `CODEMAN_PASSWORD` and gives each person a revocable credential; a non‑loopback bind and the tunnel‑enable guard are satisfied by "multi‑user with ≥1 enabled user" without a shared password.
+- **Auth is a parallel branch** (`middleware/auth.ts`) that leaves the single‑user path untouched: per‑user scrypt verify (`timingSafeEqual`, timing‑equalized against user enumeration), identity‑carrying cookies, a per‑username failure bucket (a botnet can't brute one account across IPs; one NATed user can't lock out the rest), and a `mustChangePassword` lockbox. The hook‑secret loopback bypass, host guard, and Origin/CSRF guard are unchanged (hooks authenticate the INSTANCE, not a user).
+- **Ownership is enforced server‑side only** and fails closed: `req.authUser` (a synthetic admin in single‑user), `findSessionOrFail` returns NOT_FOUND (never 403) for a foreign session, list/SSE/WS/file‑preview/search all filter by `session.owner`, and SSE routing defaults session‑scoped events to their owner (unresolved owner → withheld). The load‑bearing rule is **non‑admin `workingDir` confinement**: a non‑admin's session/one‑shot working dir must realpath‑resolve inside `~/codeman-users/<name>/cases`, checked BEFORE any disk write.
+- **Privileged actions are a one‑bit grant** (`canBypassPermissions`, default off): only granted users (and admins) get `--dangerously-skip-permissions` (others are silently downgraded to `--permission-mode auto`), shell‑mode sessions, cron `launchCommand`, and other CLIs' bypass flags. Machine‑level resources (remote/Docker host definitions, tunnel, self‑update, settings writes) are admin‑only.
+- **Admin actions are audited** append‑only to `~/.codeman/admin-audit.jsonl` (acting admin, action, target, IP). Passwords set by an admin create/reset are one‑time (returned once, force change). Under Basic auth, `logout` only truly ends QR‑issued sessions — to lock someone out, disable the account or reset the password (a proper login form is a deferred Phase 6).
+
+---
+
+## 10b. Web tabs (dashboard proxy)
+
+A saved dashboard URL renders as a tab, served through Codeman's own origin at `/webview/<capability>/`. User guide: [`web-tabs.md`](web-tabs.md). Three properties carry the security weight:
+
+- **The proxy is exempt from cookie auth and the Origin/CSRF guard, and that is deliberate.** The iframe is sandboxed without `allow-same-origin`, so it is opaque‑origin: its requests are cross‑site, meaning the `SameSite=lax` session cookie is never attached and its writes and WS upgrades arrive with `Origin: null`. The credential is instead a 192‑bit capability in the path, minted only by an authenticated `POST /api/webviews/:id/open`, held in memory (a restart invalidates every one), rolling TTL, bound to the minting user, and granting nothing but "relay bytes to this one saved URL". ⚠️ **The Host allowlist is NOT bypassed**, so DNS‑rebinding protection is unaffected. A second `Referer`‑keyed form exists for root‑absolute assets and is the only exemption decided by a request‑supplied header, so it is fenced to safe methods on non‑`/api`, non‑`/ws`, non‑`/q` paths. Edges pinned by `test/webview-auth-exemption.test.ts`.
+- **Sandboxed by default; `allow-same-origin` is an explicit per‑dashboard opt‑in.** A proxied page is same‑origin with Codeman, so without the sandbox its JavaScript could read the Codeman document and call the agent‑spawning API. ⚠️ In BOTH modes the `Authorization` header and the `codeman_session` cookie are stripped before the upstream request, because a trusted (same‑origin) frame makes the browser attach Codeman's own Basic‑auth credentials to every proxied request; forwarding them would hand `CODEMAN_PASSWORD` to the dashboard.
+- **Not an open relay, and not a privilege boundary.** `resolveUpstreamUrl()` refuses anything leaving the saved origin, and cross‑origin redirects are handed back unchanged rather than followed. The proxy does reach whatever the SERVER can reach, which is not an escalation for someone who already commands `--dangerously-skip-permissions` agents, but in multi‑user mode it means a non‑admin's dashboard is fetched from the server's network position. Saved URLs are validated to plain http(s) with no embedded credentials, and there is deliberately **no magic‑link path**: terminal output can never create a webview (the mistake the attachment scanner had to be walled off from).
+
+---
+
+## 11. Quick reference
 
 | Env / flag | Effect |
 |------------|--------|
@@ -482,6 +533,8 @@ production layout (`~/.codeman`, `-L codeman`, port 3000).
 | `--https` | Enable TLS (adds HSTS) |
 | `CODEMAN_INSTANCE` | Scope tmux socket + data dir for isolation |
 | `CODEMAN_GESTURE=1` | Make the gesture overlay available (widens CSP) |
+| `CODEMAN_DOCKER_BRIDGE_HOOKS=1` | Serve the hook endpoints on the docker bridge gateway (host‑internal, hooks‑only, `403` elsewhere) so in‑container hooks reach a loopback‑bound server — see §10 |
+| `CODEMAN_DOCKER_BRIDGE_HOST` | Override the bridge gateway IP the hooks listener binds (default: auto‑detect) |
 
 **Audit log:** session lifecycle and server start are recorded in
 `~/.codeman/session-lifecycle.jsonl`.

docs/tailscale-installer-plan.md

@@ -0,0 +1,236 @@
+# Tailscale Setup in the Installer (Plan)
+
+Goal: make "Codeman over Tailscale, with real HTTPS" a first-class, guided path in
+`install.sh`, instead of a one-line hint pointing at the docs. Today the safest
+recommended deployment (loopback bind + `tailscale serve`) is exactly what the
+maintainer's own prod runs, but a new user has to discover and wire it by hand.
+The installer should do it for them.
+
+Status: IMPLEMENTED (2026-08-04). `install.sh` carries the 3-way network
+prompt, the guided Tailscale flow, and the `tailscale` subcommand; README,
+`docs/security-architecture.md` section A, and CLAUDE.md are updated. Verified
+live on the maintainer's prod host: `install.sh tailscale` took the idempotent
+kept-as-is path against the existing serve mapping (recognizing the legacy
+`https+insecure://` target), verified `https://<node>.ts.net/api/status`
+end-to-end, and left `tailscale serve status` byte-identical. Items 1-4, 7,
+and 10-12 of the manual matrix below still need a fresh machine to exercise.
+
+## Why this is low-hanging fruit
+
+Everything on the app side already works; this is almost purely installer UX:
+
+- `.ts.net` is already in `DEFAULT_TRUSTED_HOST_SUFFIXES`
+  (`src/web/network-auth-policy.ts`), so the always-on Host/Origin guard accepts
+  `tailscale serve` traffic with zero configuration. No `CODEMAN_ALLOWED_HOSTS`
+  needed.
+- The loopback bind is the server default and prints no warning; nothing to
+  acknowledge, no `CODEMAN_PASSWORD` strictly required (the tailnet is the auth
+  boundary; Tailscale authenticates the device before a packet ever reaches us).
+- `tailscale serve` terminates TLS with a real Let's Encrypt certificate for
+  `<node>.<tailnet>.ts.net`. That gives users valid HTTPS with no self-signed
+  cert warnings, and (because it is a proper secure context) working service
+  worker, PWA install, and web push on phones. This is strictly better than
+  `codeman web --https` for remote access.
+- SSE and WebSockets work through serve (proven by prod:
+  `https://tnode.tailf80371.ts.net` fronting `127.0.0.1:3000` daily).
+- `docs/security-architecture.md` section "A. Tailscale serve (recommended)"
+  already documents this as the preferred setup; the installer just does not
+  implement it.
+
+## UX design
+
+### 1. The network-access prompt grows a Tailscale option
+
+`choose_network_binding()` (install.sh:1051) currently offers two choices. New
+menu, with Tailscale first when it can be recommended:
+
+```
+  Network access
+
+  How should the Codeman dashboard be reachable?
+
+    1) Tailscale (recommended)
+       Private VPN access from your phone/laptop, real HTTPS,
+       no password needed. Works from anywhere, not just your Wi-Fi.
+    2) Any device on your network (0.0.0.0)
+       Open it straight from your phone or laptop on the same Wi-Fi.
+       Less safe: set a password so only you control your agents.
+    3) This machine only (127.0.0.1)
+       Safest. Reach it remotely via Tailscale or a tunnel later.
+```
+
+Choice mapping:
+
+- Option 1 = bind `127.0.0.1` (unchanged server posture) + configure
+  `tailscale serve`. Internally it is option 3 plus the serve setup, so all
+  existing binding plumbing (`BIND_HOST`, service files, `read_existing_binding`)
+  is untouched.
+- Options 2 and 3 behave exactly as today (renumbered).
+- Default choice: 1 when tailscale is installed and logged in, or when an
+  existing serve mapping for our port is detected; otherwise keep today's
+  defaults (1 -> 2, 2 -> 3 renumbering, preserving the "existing setup wins"
+  rule). If tailscale is not installed, option 1 is still shown (the installer
+  offers to install it), but the default stays on the current behavior so a
+  bare Enter never pulls in new software.
+- Password: after choosing Tailscale, offer the password prompt as optional
+  defense in depth with default skip ("the tailnet already authenticates your
+  devices; add one anyway?"). No `BIND_ACK` needed since the bind is loopback.
+
+### 2. The Tailscale flow (state machine)
+
+New `setup_tailscale_access()` runs after the binding choice, before service
+setup, handling each state in order:
+
+1. **Not installed.**
+   - Linux: offer to run the official installer
+     (`curl -fsSL https://tailscale.com/install.sh | sh`), which handles all
+     distros and enables `tailscaled` at boot. This mirrors our own
+     curl-pipe-bash story and avoids maintaining per-distro logic like the six
+     `install_cloudflared_*` functions.
+   - macOS: do not auto-install (the GUI app needs an interactive login).
+     Offer `brew install --cask tailscale` when brew exists, else print the
+     download link, then wait-and-retry or let the user skip.
+   - Declined install => fall back to plain loopback (option 3 behavior) and
+     print how to redo this later (`install.sh tailscale`, see below).
+2. **Installed but logged out** (`tailscale status --json` ->
+   `.BackendState == "NeedsLogin"` or `"Stopped"`).
+   - Run `tailscale up` (via `run_as_root` if needed). It prints an auth URL
+     that works headless (user opens it on any device). Poll
+     `.BackendState == "Running"` with a friendly spinner + timeout; on
+     timeout, skip gracefully with re-run instructions.
+3. **Running: grant operator (Linux).** `sudo tailscale set --operator=$USER`
+   so serve configuration (now and in the future) does not need root. Skip
+   silently if we are already operator (probe: `tailscale serve status`
+   exits 0) or sudo is declined; fall back to `run_as_root tailscale serve ...`.
+4. **HTTPS availability check.** `.CertDomains` empty or
+   `.CurrentTailnet.MagicDNSEnabled == false` means the tailnet has not enabled
+   MagicDNS / HTTPS certificates. Print the exact two toggles with the admin
+   URL (https://login.tailscale.com/admin/dns: enable MagicDNS, then enable
+   HTTPS Certificates), then offer "I enabled it, re-check" / "skip for now".
+   No silent HTTP fallback: the pitch is real HTTPS, and a plain-HTTP serve
+   would break the PWA/push story. Skipping falls back to loopback + re-run
+   instructions.
+5. **Existing serve config check** (`tailscale serve status --json`).
+   - Already proxying to our port (443 -> `127.0.0.1:$PORT`): keep it, report
+     it, done. Re-running the installer must be idempotent.
+   - Port 443 occupied by a DIFFERENT target: never clobber it. Ask whether to
+     replace it or skip. (Prod itself has a second serve on :5000; blind
+     `tailscale serve reset` would destroy user config. NEVER use `reset`.)
+6. **Configure.** `tailscale serve --bg $PORT` where `$PORT` is the install's
+   Codeman port (default 3000; honor a preset `CODEMAN_PORT`). Serve targets
+   plain HTTP on loopback; TLS terminates at tailscaled with the real cert.
+   The `--bg` config persists in tailscaled state across reboots, so no extra
+   service unit is needed.
+   (Note: do NOT combine this with `codeman web --https`; that is what forces
+   the awkward `https+insecure://` proxy target prod historically used. New
+   installs should keep Codeman on plain HTTP behind serve.)
+7. **Verify end-to-end.** Derive the URL from `.Self.DNSName` (strip the
+   trailing dot) and curl `https://<dnsname>/api/status` after the service is
+   up, retrying for ~30s: the first request can be slow while the Let's
+   Encrypt cert is issued. Print success with the URL, or the observed error
+   with `tailscale serve status` output on failure. This follows the "always
+   test before claiming it works" rule; a blind "done!" is not acceptable.
+
+### 3. Closing summary and security notice
+
+- The final summary gains a "Remote Access (Tailscale)" block, printed above
+  the cloudflared block, showing the actual URL:
+
+  ```
+    Remote Access (Tailscale):
+      https://tnode.tailf80371.ts.net    (any device on your tailnet, HTTPS)
+      tailscale serve status             # inspect
+  ```
+
+- `print_security_notice()` third branch (loopback) gets a variant: when a
+  serve mapping for our port is detected, lead with "reachable on your tailnet
+  at https://... (HTTPS, tailnet-only)" instead of the generic "do ONE of"
+  list. Detection is dynamic (query `tailscale serve status --json` at print
+  time), no marker persisted anywhere: tailscaled's own state is the single
+  source of truth, so external changes never drift against a stale flag.
+
+### 4. Standalone entry point: `install.sh tailscale`
+
+Add a `tailscale` subcommand next to `update` / `uninstall` in the existing
+dispatch. It runs `setup_tailscale_access()` against the already-installed
+service (reads the port from the service file, requires an existing install).
+This serves:
+
+- existing installs that predate the feature,
+- users who picked "this machine only" and changed their mind,
+- every "skip for now" branch above, all of which print this exact command.
+
+One implementation, two entry points. No separate `scripts/tailscale-setup.sh`
+(unlike cloudflared, there is no long-running process for a `tunnel.sh`-style
+start/stop wrapper to manage; tailscaled owns the lifecycle).
+
+### 5. Non-interactive / automation
+
+- `CODEMAN_TAILSCALE=1` presets choice 1 (analogous to presetting
+  `CODEMAN_HOST`). In non-interactive runs it only proceeds through states
+  that need no human (already installed + logged in + HTTPS-enabled tailnet);
+  anything requiring interaction (login URL, admin-console toggle, replacing a
+  foreign serve mapping) warns and falls back to loopback. It never installs
+  tailscale non-interactively.
+- `CODEMAN_NONINTERACTIVE=1` with an existing serve mapping: preserve it, same
+  "never silently loosen/change" policy as `read_existing_binding`.
+- Document both in the header comment block of install.sh (the env-var
+  reference at the top) and in the README.
+
+## Edge cases and decisions
+
+| Case | Decision |
+| ---- | -------- |
+| macOS GUI app without `tailscale` on PATH | `get_tailscale_path()` helper mirroring `get_cloudflared_path()`: check PATH, then `/Applications/Tailscale.app/Contents/MacOS/Tailscale`. All calls go through it. |
+| Tailnet HTTPS certs disabled | Guided admin-console instructions + re-check loop; skip falls back to loopback. Never configure plain-HTTP serve. |
+| Port 443 serve exists for another app | Prompt replace/skip; never `tailscale serve reset` (destroys unrelated mappings). |
+| First cert issuance latency | Verify step retries ~30s and says why the first load may be slow. |
+| `tailscale up` needs auth | Print the auth URL prominently, poll with timeout, skip gracefully. Works headless. |
+| Custom `CODEMAN_PORT` | Serve target uses the actual port; `install.sh tailscale` re-reads it from the service file. |
+| Funnel (public internet) | OUT OF SCOPE for v1. If ever added it must mirror the tunnel guard: refuse without `CODEMAN_PASSWORD` (`isUnauthenticatedNetworkAcknowledged`). Funnel exposes to the whole internet and is a different risk class than tailnet-only serve. Mention `tailscale funnel` in docs only, with the password warning. |
+| Uninstall | Best effort: if `serve status --json` shows 443 proxying to our port, run the targeted `tailscale serve --https=443 off` (still accepted by current CLIs); if the CLI rejects it, print manual instructions. Never touch other mappings, never uninstall tailscale itself. |
+| User already fronting Codeman some other way (reverse proxy etc.) | The serve check only looks at tailscale state; other proxies are invisible and unaffected (same stance as the loopback-exemption note in security-architecture). |
+
+## What does NOT change
+
+- Server code: no changes required. Host guard already trusts `.ts.net`,
+  loopback bind is already the default, SSE/WS already work through serve.
+- The two existing binding options and their semantics, `read_existing_binding`
+  preservation, and the LAN+password flow.
+- `scripts/tunnel.sh` / cloudflared support (stays as the "no Tailscale
+  account" alternative).
+- The security model: this feature only ever narrows exposure (loopback +
+  authenticated overlay), never widens it.
+
+## Files touched (implementation inventory)
+
+| File | Change |
+| ---- | ------ |
+| `install.sh` | New: `check_tailscale`, `get_tailscale_path`, `tailscale_status_field` (jq-free JSON field extraction; the installer cannot assume jq: use `sed`/`grep` like existing helpers or `tailscale status --json` piped to `node -e` since node is guaranteed post-install), `offer_install_tailscale`, `ensure_tailscale_login`, `ensure_tailscale_operator`, `ensure_tailnet_https`, `setup_tailscale_serve`, `verify_tailscale_access`, `setup_tailscale_access` (orchestrator). Modified: `choose_network_binding` (3-way menu), summary block, `print_security_notice`, subcommand dispatch (`tailscale`), `uninstall` (targeted serve removal), header env-var docs (`CODEMAN_TAILSCALE`). |
+| `README.md` | Remote-access section: promote the Tailscale path with the one-liner and `install.sh tailscale`; keep the tailscale-IP HTTP note for non-serve users but recommend serve + HTTPS. |
+| `docs/security-architecture.md` | Section A gains "the installer can set this up for you" + `install.sh tailscale` pointer. |
+| `CLAUDE.md` | One line in Scripts & Tunnel: installer offers Tailscale setup (`install.sh tailscale` to redo). |
+| `test/` | No unit tests possible for interactive bash + a live tailnet; guard with `shellcheck install.sh` (already the norm) and the manual matrix below. |
+
+## Manual test matrix (before release)
+
+1. Linux + tailscale absent: install offered, declined => loopback fallback + hint.
+2. Linux + tailscale absent: install accepted => full flow => URL verified.
+3. Logged out => auth URL flow => Running => serve configured.
+4. Tailnet with HTTPS certs disabled => guided instructions => re-check => success; and the skip branch.
+5. Re-run installer with serve already configured => idempotent, preserved, reported.
+6. Second serve mapping on another port present => untouched (prod-like state).
+7. Port 443 already proxying another target => replace/skip prompt honored.
+8. `install.sh tailscale` on an existing loopback install (the retrofit path).
+9. `CODEMAN_NONINTERACTIVE=1` re-run => preserves everything, no prompts.
+10. macOS (Mac mini `arbbot` box): GUI-app CLI path detection + full flow.
+11. Uninstall removes only our 443 mapping, leaves others.
+12. Phone check: PWA install + push from the `https://*.ts.net` origin.
+
+## Release
+
+Changeset: `minor` (new documented installer capability + new `CODEMAN_TAILSCALE`
+env var). The feature is installer-only, so it ships with zero risk to running
+servers; `install.sh update` does not invoke the new flow (updates never rewrite
+access config), only fresh installs and the explicit `install.sh tailscale`
+subcommand do.

docs/usage-limits-display-plan.md

@@ -1,6 +1,6 @@
 # Plan Usage Limits Display — Design & As-Built
 
-> **Status: SHIPPED — deployed to prod + pushed to master, not yet released (2026-06-14).** Opt-in via App Settings → Display → **Plan Usage Limits** (`showPlanUsageLimits`, default OFF). Commits `c82f6c8` (feature) → `4d9d93d` (end-to-end fixes) → `eae225b` (per-user reconcile) → `95fb5fc` (init-snapshot replay). Full suite green (2869), CI green. No changeset/version bump yet.
+> **Status: SHIPPED — deployed to prod + pushed to master, not yet released (2026-06-14).** App Settings → Display → **Plan Usage Limits** (`showPlanUsageLimits`). **Default changed in 1.9.3: desktop now defaults ON, handhelds stay OFF, resolved via `planUsageChipEnabled()`.** The per-device notes further down describing it as opt-in/synced record the original 2026-06-14 shape, not current behavior. Commits `c82f6c8` (feature) → `4d9d93d` (end-to-end fixes) → `eae225b` (per-user reconcile) → `95fb5fc` (init-snapshot replay). Full suite green (2869), CI green. No changeset/version bump yet.
 >
 > Two surfaces from one `statusLine` callback:
 > - **Header chip** (top-right) — account-wide **plan limits**: `5h 35% · 7d 38%`, per-window green/yellow/red.

docs/versioning-policy.md

@@ -75,5 +75,5 @@ allowance. The commitments above take effect at `1.0.0`.
 ## See also
 
 - `CLAUDE.md` — the COM release workflow (changesets, version bump, deploy)
-- `SECURITY.md` — security reporting and the supported-version policy
+- `.github/SECURITY.md` — security reporting and the supported-version policy
 - `docs/security-architecture.md` — the full trust model

docs/web-tabs-fixes-plan.md

@@ -0,0 +1,190 @@
+# Web tabs: two fixes (planned + implemented 2026-07-28)
+
+Both found against the saved dashboard
+`https://<your-host>.<your-tailnet>.ts.net:4000` (Bio-Hacking-Dashboard).
+Kept because the root-cause analysis of the second one is not obvious from the
+resulting diff.
+
+Status: **both implemented and verified end-to-end.** The one deliberate
+non-change is recorded at the bottom.
+
+---
+
+## Bug 1: saved URLs could not be deleted from the Run dropdown
+
+### What happened
+
+The "Web / URL" section of the Run dropdown listed every saved dashboard as a
+single clickable row whose only action was "open". Deleting required opening the
+dashboard as a tab, clicking the tab's gear, then Delete in the modal, so a URL
+you no longer wanted open at all could not be removed without first opening it.
+
+### What shipped
+
+- `renderWebviewMenuItems()` (`src/web/public/webview-tabs.js`) now renders each
+  saved URL as a `.run-mode-row--web` flex row: the open button, a gear
+  (`showWebviewModal`), and an `x` (`deleteWebviewById`). Nested buttons are
+  invalid HTML, hence the wrapper rather than a button inside a button.
+- `deleteWebview()` split into the modal entry point, the new row entry point
+  `deleteWebviewById(id)`, and the shared `_confirmAndDeleteWebview(id)`.
+- Both side buttons call `event.stopPropagation()` so the click does not also
+  open the dashboard.
+- The dropdown's outside-click handler (`session-ui.js`) closes when the click
+  target is not inside `#runModeMenu`, and the row is gone by the time the delete
+  resolves, so `deleteWebviewById` re-asserts `.active` on the menu. Verified in a
+  browser: deleting one of several URLs leaves you looking at the rest of the list.
+- CSS in `styles.css` (`.run-mode-row--web`, `.run-mode-row-btn`) plus a larger
+  touch target in `mobile.css`. The side buttons are permanently visible rather
+  than hover-revealed, because this menu is used on touch.
+
+No server change: `DELETE /api/webviews/:id` already existed, owner-scoped, and
+already revoked the capability and broadcast `WebviewChanged`.
+
+---
+
+## Bug 2: images did not load in a proxied dashboard
+
+### Reproduction (before the fix)
+
+```
+CAP=<from POST /api/webviews/<id>/open>
+# A) upstream direct                       -> 200 image/jpeg 118150
+curl -sk "https://<your-host>.<your-tailnet>.ts.net:4000/api/hero?slug=120-minutes-in-nature"
+# B) through the proxy prefix              -> 200 image/jpeg 118150
+curl -sk "https://localhost:3000/webview/$CAP/api/hero?slug=120-minutes-in-nature"
+# C) what the browser ACTUALLY requested   -> 404 {"errorCode":"NOT_FOUND"}
+curl -sk -H "Referer: https://localhost:3000/webview/$CAP/" \
+     "https://localhost:3000/api/hero?slug=120-minutes-in-nature"
+# D) same shape but NOT under /api         -> 200 (referer fallback rescues it)
+curl -sk -H "Referer: https://localhost:3000/webview/$CAP/" "https://localhost:3000/styles.css"
+```
+
+The proxy itself was fine (B). The failure was entirely about which URL the
+browser ended up requesting (C).
+
+### Root cause
+
+The dashboard builds its image markup at runtime with root-absolute URLs:
+`c.innerHTML = '<img class="thumb" src="/api/hero?slug=...">'`, `img.src =
+slideSrc(...)` returning `/api/slide?owner=...`, `/api/story`, `/api/video`, and a
+nested `<iframe src="/api/preview?slug=...">`.
+
+All three rewrite layers missed that shape:
+
+1. `<base href="/webview/<cap>/">` only affects **relative** URLs. A root-absolute
+   `/api/hero` ignores the base path and resolves against Codeman's origin.
+2. `rewriteHtml()` only runs over the **initial HTML document**. This markup is
+   created later by page script. (The static header `<img src="/api/logo">` DID
+   work, having been rewritten at proxy time, which is why only the
+   runtime-injected images were broken.)
+3. `runtimeUrlShim()` patched only `fetch`, `XMLHttpRequest.open`, `WebSocket` and
+   `EventSource`, so the dashboard's **data** loaded while its **pictures** did
+   not.
+
+The safety net was fenced off from `/api` in two places, both deliberate:
+`server.ts`'s not-found handler returns the API-envelope 404 before reaching
+`tryWebviewRefererFallback`, and `middleware/auth.ts` refuses the Referer-form
+auth exemption for `/api/`, `/ws/`, `/q/`.
+
+### What shipped
+
+`runtimeUrlShim()` in `src/web/webview-proxy.ts` now also covers the DOM sinks, so
+a root-absolute `/api/...` request is never emitted in the first place and neither
+security fence had to move:
+
+- `innerHTML` / `outerHTML` / `insertAdjacentHTML` (and `ShadowRoot.innerHTML`),
+- `setAttribute` / `setAttributeNS`,
+- the `src`/`srcset`/`href`/`poster`/`data`/`action` property setters on img,
+  source, media, video poster, script, iframe, embed, track, link, anchor, area,
+  object and form,
+- a `MutationObserver` as a last net for any sink not patched above (it costs one
+  wasted 404 per node, since the browser starts fetching on insert, so it is a net
+  and not the mechanism).
+
+Two details that mattered:
+
+- Every rewrite routes through the existing idempotent `rw()` rather than a blind
+  prefix concat. The first draft used the server-side regex shape and
+  double-prefixed markup that was already proxied (a page re-injecting its own
+  `outerHTML`); the jsdom test caught it.
+- Everything stays inside `try`/`catch` and is marked `__cmrw`, so a double
+  injection cannot wrap an already-wrapped setter, and nothing can throw into a
+  page we do not control.
+
+### Verification
+
+- `test/webview-proxy.test.ts` gained a jsdom `runtimeUrlShim DOM sinks` block:
+  innerHTML, insertAdjacentHTML, property setters, setAttribute, srcset candidate
+  lists, the MutationObserver net via an unpatched sink
+  (`createContextualFragment`), idempotence, re-injected markup, empty `src`, and
+  the pass-throughs (relative, cross-origin, `#hash`, `data:`). 73 tests pass.
+- End-to-end in a real browser against an isolated instance
+  (`CODEMAN_INSTANCE=wvtest`, port 3151), with prod's old build as the negative
+  control:
+
+  | | before (prod, old build) | after (fixed) |
+  | --- | --- | --- |
+  | images found | 693 | 693 |
+  | src under the proxy prefix | 0 | 693 |
+  | in-viewport images decoded | 0 / 23 | 23 / 23 |
+  | sample src | `/api/hero?slug=...` | `/webview/<cap>/api/hero?slug=...` |
+
+  (The dashboard marks thumbs `loading="lazy"`, so only in-viewport images are
+  ever fetched. All 27 proxied image responses returned 200.)
+
+---
+
+## Follow-up (same day): the `/api` referer fallback, done safely
+
+Originally deferred, then implemented on request. Both gates had to move, and the
+auth one is the security-sensitive half: auth runs in `onRequest`, before routing,
+so it cannot tell a real Codeman API route from a 404, and simply dropping the
+`/api` fence would let a page holding a capability forge a `Referer` and reach
+Codeman's **real** API unauthenticated.
+
+What shipped:
+
+- `server.ts`: `tryWebviewRefererFallback` is tried **before** the API-shaped 404.
+  Reaching that handler already proves no route matched, and the relay declines
+  unless the `Referer` carries a live capability, so unknown `/api` paths still
+  get the envelope.
+- `middleware/auth.ts`: the `/api/` prefix refusal is replaced by
+  `matchesRegisteredRoute()`, which refuses the exemption for any path that
+  resolves to a real route. `/ws/` and `/q/` stay refused by prefix.
+
+Two findings that decided the implementation, both established by probing Fastify
+rather than by reading its docs:
+
+- **`hasRoute()` is the wrong tool and would have been a hole.** It matches the
+  registered PATTERN literally, so `hasRoute({url: '/api/sessions/abc'})` returns
+  false against a registered `/api/sessions/:id` and would have handed out an
+  exemption on a live, session-scoped API route. `findRoute()` performs the real
+  radix-tree lookup and is what the fence uses.
+- **`@fastify/static` is mounted at `/`, so it registers a root catch-all that
+  matches every path.** A match on it means "heading for the 404 handler", not
+  "real route", and it is distinguishable because a root catch-all is the only
+  route whose `*` param comes back equal to the whole request path. Without that
+  carve-out the fence would have refused every referer-form request and broken the
+  rescue that already worked.
+
+The fence fails closed, and `test/webview-auth-exemption.test.ts` pins both edges
+(a concrete URL onto a parametric API route stays 401; the dashboard's own
+`/api/...` namespace is served).
+
+### And the CSS gap, which the fallback could NOT close
+
+Testing the fallback against a purpose-built upstream showed the runtime-injected
+stylesheet case is unreachable by any relay: a `<style>` element has no URL of its
+own, so Chromium sends an **empty `Referer`** with the image request it triggers
+and there is nothing to key on. Measured directly:
+
+| sink | Referer the browser sends | fixed by |
+| --- | --- | --- |
+| `url()` in a proxied `.css` | the stylesheet's proxied URL | the referer relay |
+| `url()` in a runtime `<style>` | *empty* | `rwCss()` in the shim |
+
+So the shim also rewrites `url()` inside `<style>` blocks, both when they arrive as
+markup and when a `<style>` node is inserted (via the existing MutationObserver).
+
+The only gap left is self-navigation via `location.href = '/x'`, which cannot be
+patched because `Location.href` is unforgeable.

docs/web-tabs.md

@@ -0,0 +1,155 @@
+# Web Tabs (dashboards as Codeman tabs)
+
+Open any dashboard you run, Grafana, Uptime Kuma, Portainer, a status page on port
+4000, as a tab beside your Claude/Codex/Gemini sessions. Codeman becomes one mission
+control instead of Codeman plus a pile of browser tabs.
+
+## Using it
+
+1. Click the chevron next to **Run** to expand the dropdown.
+2. Under **Web / URL**, pick **Add dashboard...**
+3. Give it a name and a URL, optionally hit **Test**, then **Save**.
+
+The dashboard opens as a tab immediately, and appears in the Run dropdown from then
+on. Web tabs sit in the same strip as session tabs, continue the same `Alt+1..9`
+numbering, and carry a globe icon so they never read as a running agent.
+
+Closing a tab (the `x`) only closes it. The saved dashboard stays in the dropdown.
+To delete it for good, use the `x` on its **dropdown row** (the tab's own `x` is
+close, not delete). Each dropdown row also has a gear for editing, so a saved URL
+can be changed or removed without opening it first.
+
+Switching tabs does **not** reload a dashboard. Frames stay alive in the background,
+so a dashboard that took a while to authenticate is still there when you come back.
+Past six live frames the least-recently-viewed one is dropped to bound memory
+(`CODEMAN_MAX_LIVE_WEBVIEW_FRAMES`).
+
+## Why dashboards are proxied
+
+A plain `<iframe src="http://your-box:4000">` does not work in the setup Codeman
+actually ships in, for three separate reasons:
+
+| Blocker             | What happens                                                                                   |
+| ------------------- | ---------------------------------------------------------------------------------------------- |
+| **Mixed content**   | Production serves HTTPS (behind `tailscale serve`). Browsers hard-block `http://` iframes on an HTTPS page, with no override, and none at all on iOS Safari. |
+| **Framing refusal** | Grafana, Portainer, Home Assistant and many others send `X-Frame-Options: DENY` or `frame-ancestors 'none'`. |
+| **Codeman's CSP**   | `default-src 'self'` means `frame-src` falls back to `'self'`, so a cross-origin iframe is blocked before it starts. |
+
+Serving the dashboard **through Codeman's own origin** dissolves all three. So by
+default a web tab loads `/webview/<capability>/` on Codeman, and Codeman relays to
+the dashboard: stripping the framing refusal, rewriting redirects, cookies and
+root-absolute URLs, and relaying WebSockets so live panels actually update.
+
+A useful consequence: the dashboard is fetched **from the Codeman server**, so a
+tailnet-only or `localhost`-only dashboard works from any device that can reach
+Codeman, including a phone that is not on the tailnet.
+
+`direct` mode (a plain cross-origin iframe) still exists and is cheaper, but it only
+works for an HTTPS dashboard that permits framing. The **Test** button probes from
+the server and tells you which mode applies.
+
+## The sandbox, and when to turn it off
+
+Because a proxied dashboard is served from Codeman's own address, it is
+*same-origin with Codeman* as far as the browser is concerned. Left unchecked, its
+JavaScript could read the Codeman page and call the API that spawns agents.
+
+So the iframe is sandboxed **without** `allow-same-origin` by default. The page runs
+in an opaque origin: it cannot touch Codeman, and it gets no cookies or
+`localStorage` of its own.
+
+Unchecking **Open sandboxed** grants `allow-same-origin`. Do that only for a
+dashboard you fully trust, and only if you need it, which in practice means a
+dashboard with its own login that stores a session in a cookie or `localStorage`.
+
+Even in trusted mode, Codeman never forwards its own credentials upstream: the
+`Authorization` header and the `codeman_session` cookie are stripped on the way out,
+so `CODEMAN_PASSWORD` cannot leak into a dashboard.
+
+## How the proxy authenticates
+
+A sandboxed iframe is opaque-origin, so every request it makes is cross-site: the
+`SameSite=lax` session cookie is not sent, and writes and WebSocket upgrades arrive
+with `Origin: null`. Cookie auth cannot work.
+
+Instead, opening a dashboard mints a **capability**: 192 bits of entropy in the URL
+path, held in memory only, with a rolling 12-hour TTL, bound to the user who minted
+it, and granting exactly one thing, relaying bytes to that one saved URL. Editing or
+deleting a dashboard revokes it, and a server restart invalidates every outstanding
+capability (tabs re-mint transparently on next click).
+
+## Limits and env vars
+
+| Variable                             | Default | Meaning                                    |
+| ------------------------------------ | ------- | ------------------------------------------ |
+| `CODEMAN_MAX_WEBVIEWS`               | 50      | Saved dashboards per owner                 |
+| `CODEMAN_MAX_LIVE_WEBVIEW_FRAMES`    | 6       | Iframes kept mounted at once               |
+| `CODEMAN_WEBVIEW_CAPABILITY_TTL_MS`  | 12h     | Rolling capability lifetime                |
+| `CODEMAN_WEBVIEW_TIMEOUT_MS`         | 30000   | Upstream request timeout                   |
+| `CODEMAN_WEBVIEW_PROBE_TIMEOUT_MS`   | 8000    | Timeout for the Test button                |
+| `CODEMAN_MAX_WEBVIEW_HTML_BYTES`     | 8MB     | Largest HTML document rewritten            |
+| `CODEMAN_MAX_WEBVIEW_SOCKETS`        | 8       | Concurrent proxied WebSockets per dashboard |
+
+Saved dashboards live in `~/.codeman/webviews.json`. Which tabs you have open is
+per-device (`localStorage`), since that is workspace layout rather than config.
+
+## How a dashboard's own API calls keep working
+
+Worth knowing, because it is where this feature does its least obvious work. Three
+layers cooperate so a dashboard talking to its own backend just works:
+
+1. `<base href>` handles relative URLs in the markup.
+2. Attribute rewriting handles root-absolute `src`/`href`/`action` in the page the
+   proxy serves.
+3. A small injected script rebases URLs built at **runtime**, which the first two
+   cannot see: `fetch('/api/data')` and `new WebSocket('/live')`, but equally
+   `card.innerHTML = '<img src="/api/hero">'`, `img.src = '/api/slide'`, and
+   `url(/img.png)` inside a `<style>` the page injects. That second group is why
+   images are covered too. A dashboard that renders its thumbnails from script
+   would otherwise show all its data and none of its pictures, because `<base>`
+   does not apply to root-absolute URLs and the attribute rewriting only ever saw
+   the initial document.
+4. As a last resort, a request that still lands on Codeman's own root is relayed
+   using its `Referer` to identify the dashboard. This only fires for a request
+   that already missed every Codeman route, and never for one that resolves to a
+   real route, which is what keeps it from being an authentication bypass.
+
+On top of that, the proxy answers those requests with CORS headers. That sounds
+wrong for same-host requests, but a sandboxed iframe has an *opaque* origin, so the
+browser treats every one of its `fetch`/XHR calls as cross-origin even though the
+URL is on Codeman itself. Without those headers, a dashboard renders perfectly and
+then every API call fails, which looks like the dashboard being broken.
+
+## Known limits
+
+- **Exotic loaders.** The layers above cover normal `fetch`/XHR/WebSocket/
+  EventSource, normal markup, the DOM sinks a page uses to build markup at runtime,
+  and `url()` inside stylesheets. Something that constructs requests by an unusual
+  route can still slip through. Symptom: the page renders but a panel stays empty.
+- **Root-absolute `location` navigation.** A dashboard that navigates itself with
+  `location.href = '/login'` escapes the prefix, because `Location.href` is
+  unforgeable and cannot be patched the way the other sinks are. A relative
+  `location.href = 'login'` is fine (`<base>` covers it).
+- **Cross-origin redirects are not followed.** If a dashboard bounces to a different
+  host (an external SSO provider, say), the proxy hands the redirect back unchanged
+  rather than relaying it, because relaying would make this an open proxy. Use
+  **Open in new tab** for those.
+- **Login-protected dashboards need trusted mode**, since a sandboxed frame has no
+  cookie jar. A server-side per-dashboard cookie jar would lift this and is the
+  natural next step if it becomes annoying.
+- **Not a security boundary.** The proxy reaches whatever the Codeman server can
+  reach. That is not an escalation for someone who already commands
+  `--dangerously-skip-permissions` agents, but in multi-user mode it does mean a
+  non-admin user's dashboard is fetched from the server's network position.
+
+## Where the code lives
+
+| Concern                  | File                                    |
+| ------------------------ | --------------------------------------- |
+| Pure rewrite helpers     | `src/web/webview-proxy.ts`              |
+| Routes + proxy + sockets | `src/web/routes/webview-routes.ts`      |
+| Capability tokens        | `src/webview-capabilities.ts`           |
+| Persistence              | `src/webview-store.ts`                  |
+| Limits                   | `src/config/webview-limits.ts`          |
+| Frontend                 | `src/web/public/webview-tabs.js`        |
+| Auth exemption           | `src/web/middleware/auth.ts`             |

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "aicodeman",
-  "version": "1.4.0",
+  "version": "1.10.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "aicodeman",
-      "version": "1.4.0",
+      "version": "1.10.0",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [
@@ -34,6 +34,7 @@
         "qrcode": "^1.5.4",
         "uuid": "^14.0.0",
         "web-push": "^3.6.7",
+        "ws": "^8.21.0",
         "zod": "^4.3.6"
       },
       "bin": {
@@ -12332,7 +12333,7 @@
       }
     },
     "packages/xterm-zerolag-input": {
-      "version": "0.1.4",
+      "version": "0.1.8",
       "license": "MIT",
       "devDependencies": {
         "jsdom": "^24.1.3",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "aicodeman",
-  "version": "1.4.0",
+  "version": "1.10.0",
   "description": "Mission control for AI coding agents - run 20 autonomous agents with real-time monitoring and session persistence",
   "type": "module",
   "main": "dist/index.js",
@@ -22,6 +22,7 @@
     "test:coverage": "vitest run --config config/vitest.config.ts --coverage",
     "test:ci": "vitest run --config config/vitest.ci.config.ts",
     "check:frontend-syntax": "node scripts/check-frontend-syntax.mjs",
+    "fix:node-pty": "node scripts/fix-node-pty.mjs",
     "typecheck": "tsc --noEmit",
     "lint": "eslint --config config/eslint.config.js 'src/**/*.ts'",
     "lint:fix": "eslint --config config/eslint.config.js 'src/**/*.ts' --fix",
@@ -32,25 +33,44 @@
     "changeset": "changeset",
     "version-packages": "changeset version && npm install --package-lock-only && node scripts/check-lockfile-sync.mjs",
     "check:lockfile": "node scripts/check-lockfile-sync.mjs",
-    "knip": "npx --yes knip@latest",
+    "knip": "npx --yes knip@latest --config config/knip.json",
     "release": "changeset publish"
   },
+  "prettier": {
+    "singleQuote": true,
+    "semi": true,
+    "tabWidth": 2,
+    "printWidth": 120,
+    "trailingComma": "es5",
+    "endOfLine": "lf"
+  },
   "workspaces": [
     ".",
     "packages/*"
   ],
   "keywords": [
-    "claude",
     "claude-code",
+    "claude-ai",
+    "claude",
     "anthropic",
-    "ai-agent",
-    "automation",
+    "opencode",
+    "codex",
+    "gemini-cli",
+    "ai-agents",
+    "agent",
     "session-manager",
+    "self-hosted",
+    "developer-tools",
+    "tmux",
     "terminal",
+    "xterm",
+    "docker",
+    "mosh",
+    "local-echo",
+    "web-dashboard",
     "cli",
     "llm",
-    "autonomous-agent",
-    "ralph-loop"
+    "automation"
   ],
   "author": "arkon",
   "license": "MIT",
@@ -75,6 +95,7 @@
     "qrcode": "^1.5.4",
     "uuid": "^14.0.0",
     "web-push": "^3.6.7",
+    "ws": "^8.21.0",
     "zod": "^4.3.6"
   },
   "devDependencies": {
@@ -136,6 +157,7 @@
   "files": [
     "dist",
     "scripts/postinstall.js",
+    "scripts/fix-node-pty.mjs",
     "LICENSE",
     "README.md"
   ]

packages/xterm-zerolag-input/CHANGELOG.md

@@ -1,5 +1,69 @@
 # xterm-zerolag-input
 
+## 0.1.8
+
+### Patch Changes
+
+- **Fixed: sessions failed to start on macOS with `Error: posix_spawnp failed.`** (issues #6 and #204)
+
+  `node-pty@1.1.0` publishes its macOS prebuilt helper as `prebuilds/darwin-<arch>/spawn-helper` with mode 0644, i.e. no execute bit. macOS launches every PTY through that helper, so a stock install failed on every session start. The bug is macOS-only: `spawn-helper` is a mac-only gyp target and node-pty ships no Linux prebuild, so Linux always compiles a correctly-permissioned helper from source.
+
+  The previous fix chmodded only `build/Release/spawn-helper`, which on macOS does not exist (the prebuild is used, so node-gyp never runs), and it derived that path from `require.resolve('node-pty')`, landing on `<pkg>/lib/build/Release/...`. It was a no-op on every platform.
+  - New `scripts/fix-node-pty.mjs` (also `npm run fix:node-pty`) chmods every `spawn-helper` it finds, in `build/Release`, `build/Debug` and each `prebuilds/*/`, then verifies the result by actually opening a PTY. A `require()` alone passes on a broken install, because the helper is only touched at spawn time.
+  - `postinstall` no longer force-rebuilds node-pty from source on Node 22+. That step needed Xcode command line tools, cost 30-120s on every install, and deleted the `prebuilds/` tree before compiling, so a Mac without a compiler was left with no working binary at all. A rebuild now happens only when the chmod plus spawn probe still fails, and the prebuilds tree is backed up and restored around it.
+  - New `spawnPtyWithHelperRepair()` (`src/utils/node-pty-repair.ts`) wraps every `pty.spawn()` in `session.ts`, so an install that is already broken repairs itself on the first failed spawn and retries in-process instead of showing a dead session. Unrelated spawn errors are rethrown untouched; a second failure carries the `npm run fix:node-pty` hint.
+  - `scripts/fix-node-pty.mjs` is now in the published `files` list, so global npm installs get the repair too.
+  - Direct-PTY Claude spawns use the resolved absolute binary path (new `getClaudeBinaryPath()`) instead of the bare name `claude`, so a CLI installed outside the server's PATH still launches.
+
+  Verified end to end on macOS 26.4 arm64: a stock `npm i` reproduces `posix_spawnp failed.`, and after the fix the same install spawns a PTY successfully with the prebuilds preserved.
+
+  **Added: phone home screen (session overview)**
+
+  Under 430px the "C" logo now opens a session overview (current sessions, past sessions, spaces) instead of the welcome overlay: on a small screen "which session needs me" beats "how do I start one". Rows resume a session in place, and "New session here" goes through the normal quick-start path so remote and Docker cases keep their routing. Per-device setting `mobileOverviewEnabled` (phones only, default ON) in App Settings. Tablet and desktop are unchanged.
+
+  **Added: guided Tailscale setup in `install.sh`**
+
+  The network-access prompt is now 3-way: Tailscale, LAN, or local-only. The Tailscale path binds loopback and walks through installing Tailscale, logging in, the operator grant, the tailnet HTTPS-certificates toggle, and `tailscale serve --bg <port>`, then verifies the result end to end with curl. That gives HTTPS on a real certificate with no app password and no `0.0.0.0` bind, which is also what PWA install and web push need. `install.sh tailscale` retrofits it onto an existing install, and `CODEMAN_TAILSCALE=1` presets the choice. Serve state is detected from `tailscale serve status --json`; the installer never runs `tailscale serve reset` and never touches serve mappings other than 443 to Codeman's port. README and `docs/security-architecture.md` updated to match.
+
+  **Docs**: replaced a real tailnet hostname with placeholders in `docs/web-tabs-fixes-plan.md`.
+
+  **xterm-zerolag-input**: npm description and keywords only, no code change.
+
+## 0.1.7
+
+### Patch Changes
+
+- Fix a latent bug where a partial settings PUT silently reset live service state, and trim the `xterm-zerolag-input` README callout.
+  - **`PUT /api/settings` no longer resets watchers on a partial body.** The three `toggleService` calls (subagent watcher, workflow-run watcher, image watcher) read the raw request body with `??` defaults, so every key a caller omitted was treated as "apply the default". A body of just `{statusLineTelemetry:true}` would START the subagent watcher and STOP the workflow and image watchers, undoing the persisted config. They now resolve from `merged` (persisted settings + incoming), the same convention the `tmuxHistoryLimit` branch in that handler already used, so any PUT reconciles services to the effective stored state. Nothing triggered this in practice because every shipped client sends a full settings payload rebuilt from the DOM, but it was a trap for the next partial-update caller.
+  - **Regression test**: `test/routes/system-routes-settings-partial-put.test.ts` (4 cases) pins both directions, omitted keys preserve state and explicit keys still take effect. Verified to fail against the pre-fix handler.
+  - **CLAUDE.md** records the rule under "Adding Features → App setting": anything acting on a setting in that handler must resolve from `merged`, never the request body.
+  - **`xterm-zerolag-input` README**: removed the links line (getcodeman.com / install one-liner / star link) from the Codeman callout above the demo GIF. The callout keeps its links in the heading and body.
+
+## 0.1.6
+
+### Patch Changes
+
+- Plan-usage chip now defaults ON on desktop, plus the reworked `xterm-zerolag-input` README.
+  - **Plan-usage chip defaults ON (desktop).** The `showPlanUsageLimits` chip (live 5-hour and weekly plan usage from the Claude statusline) used to be opt-in and default OFF, so most users never saw it. Desktop now defaults ON; handhelds still default OFF so the phone header stays minimal and the `mobile-header-buttons-policy` guard keeps passing. Devices with an explicitly stored preference keep whatever they chose, so nobody's OFF gets overridden.
+  - **One resolver behind the chip.** Added `planUsageChipEnabled()` in settings-ui.js and routed all three call sites through it: the App Settings checkbox, the chip's visibility, and the create-time `statusLineTelemetry` flag in session-ui.js. Those three had independent `?? false` / `=== true` defaults, and a chip revealed without the telemetry flag renders `—` forever, so a default flip on one site alone would have shipped a permanently empty chip.
+  - **Cron button comment corrected.** The App Settings comment claimed "Cron button defaults ON" while the code, the template (`btn-cron--hidden`) and the CSS all default it OFF. Verified against a fresh browser profile: the button is hidden and its checkbox unchecked out of the box. Comment now matches, and states why the two halves stay consistent.
+  - **Docs.** CLAUDE.md, `docs/architecture-invariants.md` and `docs/usage-limits-display-plan.md` updated for the new default and the single-resolver rule; the stale `styles.css` comment claiming the server strips the chip's hidden class at render was corrected (display is per-device, so the client reveals it).
+  - **`xterm-zerolag-input` README rework** (0.1.5 shipped the content; this republishes with the graphic and promo changes): replaced the misaligned 8-line keystroke-flow diagram with a two-line stock-vs-zerolag contrast, added a Codeman callout above the demo GIF with links to getcodeman.com and the repo, and rewrote the Origin section so it argues the extraction story instead of repeating the promo.
+
+## 0.1.5
+
+### Patch Changes
+
+- Rewrite the `xterm-zerolag-input` package README as a value-first document and correct the drift that had accumulated against the source.
+  - Added the side-by-side phone demo GIF (`docs/images/zerolag-demo-20260728.gif`) as the hero image, referenced by absolute raw URL so it renders on npmjs.com as well as GitHub. The two-phone comparison shows 0ms local echo next to a 600ms-2.7s server echo on the same session.
+  - New "Why this one" comparison table, an explicit list of target use cases (SSH web clients, cloud IDEs, mobile terminals, container consoles), and a bundle-size badge (6.1 kB gzipped, measured from the ESM build).
+  - Corrected the test-count badge from 78 to the actual 175 tests across 5 files, in both the package README and the Published Packages section of the root README.
+  - Removed the stale "Unicode/emoji rendered at single-cell width" limitation. CJK, fullwidth forms and emoji have had double-width rendering and visual-column positioning since the wide-character fix; the honest remaining caveat (per-code-point width summing over-counts ZWJ grapheme clusters) replaces it.
+  - Documented the previously undocumented public `setPrompt()` method for switching prompt strategies at runtime, and the new "Wide characters (CJK, emoji)" integration section covering the optional `Unicode11Addon` path and the built-in range-table fallback.
+  - Documented `backgroundColor: 'transparent'`, corrected the `foregroundColor` default, and updated the grid-alignment math to reflect visual-column positioning rather than character index.
+
+  No source changes, docs only.
+
 ## 0.1.4
 
 ### Patch Changes

packages/xterm-zerolag-input/README.md

@@ -1,45 +1,64 @@
 <p align="center">
   <h1 align="center">xterm-zerolag-input</h1>
   <p align="center">
-    Instant keystroke feedback overlay for <a href="https://xtermjs.org/">xterm.js</a><br>
-    <em>Eliminates perceived input latency over high-RTT connections</em>
+    <strong>Make typing feel instant in <a href="https://xtermjs.org/">xterm.js</a>, no matter how far away the server is.</strong><br>
+    <em>A pixel-perfect local echo overlay. Client-side only. Zero dependencies.</em>
   </p>
   <p align="center">
     <a href="https://www.npmjs.com/package/xterm-zerolag-input"><img src="https://img.shields.io/npm/v/xterm-zerolag-input?style=flat-square&color=22c55e" alt="npm"></a>
     <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-1e3a5f?style=flat-square" alt="MIT"></a>
-    <img src="https://img.shields.io/badge/Dependencies-0-22c55e?style=flat-square" alt="Zero deps">
-    <img src="https://img.shields.io/badge/Tests-78-22c55e?style=flat-square" alt="78 tests">
-    <img src="https://img.shields.io/badge/xterm.js-v5%20%7C%20v7+-3b82f6?style=flat-square" alt="xterm.js">
+    <img src="https://img.shields.io/badge/Dependencies-0-22c55e?style=flat-square" alt="Zero dependencies">
+    <img src="https://img.shields.io/badge/Size-6.1%20kB%20gzip-22c55e?style=flat-square" alt="6.1 kB gzipped">
+    <img src="https://img.shields.io/badge/Tests-175-22c55e?style=flat-square" alt="175 tests">
+    <img src="https://img.shields.io/badge/xterm.js-v5%20%7C%20v7+-3b82f6?style=flat-square" alt="xterm.js v5 and v7+">
   </p>
 </p>
 
+> ### Made for [**Codeman**](https://getcodeman.com)
+>
+> This overlay is the local echo engine of [**Codeman**](https://github.com/Ark0N/Codeman), mission control for AI coding agents: run and monitor a dozen Claude Code, Codex, OpenCode and Gemini sessions at once, watch their subagents work in live floating windows, let them run autonomously overnight, and drive all of it from your phone.
+>
+> That last part is why this library exists. The demo below is a real Codeman session on two phones.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/Ark0N/Codeman/master/docs/images/zerolag-demo-20260728.gif" alt="Side-by-side phones typing into the same remote session: with zerolag the text appears at 0ms, without it every keystroke waits 600ms to 2.7s for the server echo" width="900">
+</p>
+
+<p align="center">
+  <em>Two phones, the same remote session, the same slow link.<br>
+  Left: the zerolag overlay paints every keystroke at <strong>0ms</strong>. Right: stock xterm.js waits <strong>600ms to 2.7s</strong> for the server to echo it back.</em>
+</p>
+
 ---
 
-## The Problem
+## The 30-second version
 
-When using xterm.js over a remote connection (SSH web clients, cloud IDEs, mobile terminals), every keystroke takes a full round-trip to the server before appearing on screen. At 100-500ms RTT, typing feels sluggish and unresponsive. Users type blind, make mistakes they can't see, and the experience feels broken.
-
-## The Solution
-
-`xterm-zerolag-input` renders typed characters **immediately** as a pixel-perfect DOM overlay positioned on the terminal's character grid. The overlay covers the terminal canvas at the prompt location, showing characters instantly while the server echo travels back. Once the server responds, the overlay seamlessly disappears and the real terminal text takes over.
+Over a remote connection, xterm.js shows you a character only after it has flown to the server and back. At 100-500ms RTT that reads as broken: you type ahead of the screen, you cannot see your typos, and you start pecking one key at a time to stay in sync.
 
 ```
-Keystroke Flow:
-                                    ┌─── DOM overlay (instant, 0ms)
-User types 'h' ─── onData('h') ───┤
-                                    └─── Your app sends to PTY ──→ Server
-                                                                      │
-Server echoes 'h' ←──────────────────────────────────────────────────┘
-         │                                                  (200-500ms RTT)
-         └──→ terminal.write('h') ──→ overlay.clear()
-              (server output replaces overlay — seamless transition)
+  stock xterm.js   keypress ─────── 300 ms ───────→ character appears
+  with zerolag     keypress → character appears  ·  echo lands later, unseen
 ```
 
-**No changes to your backend needed.** The addon is purely client-side.
+Same keystroke, same link. The only difference is who you wait for: the server, or nobody.
 
-## Origin
+`xterm-zerolag-input` paints your keystrokes **immediately**, as an absolutely-positioned DOM overlay locked to the terminal's character grid. The byte still goes to the PTY exactly as before, so nothing about your shell changes. When the server echo lands 300ms later, the overlay clears and the real terminal text takes over on the same pixels. The handoff is invisible.
 
-This library was extracted from [Codeman](https://github.com/Ark0N/Codeman), mission control for AI coding agents — multi-session management, real-time agent visualization, autonomous respawn loops, and a mobile-first web UI for Claude Code, OpenCode, and Codex. The local echo system was built to make mobile and remote access feel instant, then battle-tested across thousands of hours of real usage. After 3 deep code audits, it was extracted into this standalone library with 78 tests covering every state transition.
+**No backend changes. No protocol. No server support.** It is a client-side addon that never touches the wire.
+
+## Why this one
+
+| | |
+|---|---|
+| **Survives full-screen TUIs** | Ink, blessed, and friends repaint the whole screen constantly. The overlay is a separate DOM layer they cannot reach, so it does not get clobbered. |
+| **Pixel-matched to the canvas** | Each character is its own absolutely-positioned `<span>` at exact cell coordinates, so it does not drift out of the grid like normal DOM text flow. |
+| **Wide characters included** | CJK, fullwidth forms and emoji render double-width and position by visual column, using the terminal's Unicode addon when one is loaded. |
+| **Backspace that actually works** | A three-layer cascade (unsent, in-flight, already on screen) tells you exactly what to forward to the PTY, so editing works through any mix of typed, flushed and tab-completed text. |
+| **You keep control of input** | The addon never hooks `onData` for you. You decide what gets echoed and what gets forwarded, which is what makes char-at-a-time, buffered, and multi-session tab switching all possible. |
+| **Small and self-contained** | 6.1 kB gzipped, zero runtime dependencies, dual CJS/ESM with full type declarations. |
+| **Proven under load** | Extracted from [Codeman](https://getcodeman.com), hardened over thousands of hours of real remote and mobile usage, 175 tests over every state transition. |
+
+Built for anything that puts a terminal behind a network hop: SSH web clients, cloud IDEs, mobile terminals, Kubernetes and container consoles, remote agent dashboards, browser-based dev environments.
 
 ## Install
 
@@ -47,12 +66,9 @@ This library was extracted from [Codeman](https://github.com/Ark0N/Codeman), mis
 npm install xterm-zerolag-input
 ```
 
-- **Zero runtime dependencies**
-- Compatible with both `xterm` (pre-5.4) and `@xterm/xterm` (5.4+)
-- Dual CJS/ESM build with full TypeScript declarations
-- Works with canvas, WebGL, and DOM renderers
+Works with both `xterm` (pre-5.4) and `@xterm/xterm` (5.4+), and with the canvas, WebGL and DOM renderers.
 
-## Quick Start
+## Quick start
 
 ```typescript
 import { Terminal } from '@xterm/xterm';
@@ -61,7 +77,7 @@ import { ZerolagInputAddon } from 'xterm-zerolag-input';
 const terminal = new Terminal();
 terminal.open(document.getElementById('terminal')!);
 
-// 1. Create addon with your prompt character
+// 1. Create the addon with your prompt character
 const zerolag = new ZerolagInputAddon({
   prompt: { type: 'character', char: '$', offset: 2 },
 });
@@ -75,7 +91,7 @@ terminal.onData((data) => {
     ws.send(text + '\r');
   } else if (data === '\x7f') {
     const source = zerolag.removeChar();
-    if (source === 'flushed') ws.send(data); // only backspace text already in PTY
+    if (source === 'flushed') ws.send(data); // only backspace text already in the PTY
   } else if (data.length === 1 && data.charCodeAt(0) >= 32) {
     zerolag.addChar(data);
   }
@@ -87,26 +103,29 @@ terminal.onWriteParsed(() => {
 });
 ```
 
-## Why This Is Hard
+That is the whole integration. Everything below is for tuning it.
 
-Most terminal UIs can't do local echo because:
+## Why this is hard
 
-1. **Buffer writes corrupt**: Frameworks like [Ink](https://github.com/vadimdemedes/ink) (React for terminals) redraw the entire screen on every state change. Writing directly to the terminal buffer gets immediately overwritten.
+Most terminal UIs cannot do local echo, for three reasons:
 
-2. **Cursor position lies**: In Ink, `buffer.cursorY` reflects internal state (near the status bar), not the visible prompt. You can't trust it.
+1. **Buffer writes get corrupted.** Frameworks like [Ink](https://github.com/vadimdemedes/ink) (React for terminals) redraw the entire screen on every state change. Anything written straight into the terminal buffer is overwritten immediately.
 
-3. **Font matching**: Canvas/WebGL renderers use their own text shaping. A DOM overlay must pixel-match the canvas grid — normal DOM text flow drifts due to sub-pixel glyph width differences.
+2. **Cursor position lies.** In Ink, `buffer.cursorY` reflects internal render state (often near a status bar), not the visible prompt. You cannot trust it.
 
-This library solves all three by:
-- Using a **DOM overlay** that Ink can't touch (separate z-index layer)
-- **Scanning the buffer** bottom-up for the prompt character instead of trusting cursor position
-- Rendering each character as an **absolutely-positioned `<span>`** at exact cell-grid coordinates
+3. **Fonts do not line up.** Canvas and WebGL renderers do their own text shaping. A DOM overlay has to pixel-match that grid, and normal DOM text flow drifts as sub-pixel glyph widths accumulate.
+
+This library answers all three:
+
+- a **DOM overlay** on its own z-index layer, which Ink cannot touch
+- **bottom-up buffer scanning** for the prompt instead of trusting the cursor
+- **one absolutely-positioned `<span>` per character** at exact cell-grid coordinates
 
 ---
 
-## Prompt Detection
+## Prompt detection
 
-The addon needs to know where user input starts. It scans the terminal buffer bottom-up for the prompt. Three strategies:
+The addon needs to know where user input starts. It scans the terminal buffer bottom-up. Three strategies:
 
 ### Character (default)
 
@@ -118,17 +137,17 @@ The addon needs to know where user input starts. It scans the terminal buffer bo
 { type: 'character', char: '%', offset: 2 }
 
 // Fish / Starship: ❯
-{ type: 'character', char: '\u276f', offset: 2 }
+{ type: 'character', char: '❯', offset: 2 }
 
 // Simple arrow: >
 { type: 'character', char: '>', offset: 2 }
 ```
 
-`offset` = characters between the prompt marker and where user input begins (e.g., `"$ "` = 2).
+`offset` = characters between the prompt marker and where user input begins (`"$ "` = 2).
 
 ### Regex
 
-For complex prompts. The `g` flag is safely stripped to prevent `lastIndex` mutation.
+For complex prompts. The `g` flag is stripped safely, so there is no `lastIndex` mutation.
 
 ```typescript
 { type: 'regex', pattern: /\$\s*$/, offset: 2 }
@@ -150,77 +169,88 @@ Full control:
 }
 ```
 
+### Switching prompts at runtime
+
+If one terminal hosts several CLIs with different prompts, swap the strategy in place:
+
+```typescript
+zerolag.setPrompt({ type: 'character', char: '❯', offset: 2 });
+```
+
+`setPrompt()` clears the cached prompt position and re-renders if anything is pending, so a mode switch cannot leave the overlay pinned to the old column.
+
 ---
 
-## API Reference
+## API reference
 
 ### `ZerolagInputAddon`
 
-Implements xterm.js `ITerminalAddon`. The addon does **not** hook `terminal.onData()` — you wire your own input handler and call these methods. This gives you full control over which keystrokes are echoed vs forwarded.
+Implements the xterm.js `ITerminalAddon` interface. It deliberately does **not** hook `terminal.onData()`: you wire your own handler and call these methods, which is what gives you control over which keystrokes are echoed and which are forwarded.
 
 ### Input
 
 | Method | Returns | Description |
 |--------|---------|-------------|
-| `addChar(char)` | `void` | Add a single printable character. Auto-detects existing buffer text on first keystroke. |
+| `addChar(char)` | `void` | Add a single printable character. Auto-detects existing buffer text on the first keystroke. |
 | `appendText(text)` | `void` | Append multiple characters (paste). |
-| `removeChar()` | `'pending'` \| `'flushed'` \| `false` | Remove last char. See [backspace handling](#backspace-handling). |
-| `clear()` | `void` | Clear all state, hide overlay. Call on Enter/Ctrl+C/Escape. |
+| `removeChar()` | `'pending'` \| `'flushed'` \| `false` | Remove the last character. See [backspace handling](#backspace-handling). |
+| `clear()` | `void` | Clear all state and hide the overlay. Call on Enter, Ctrl+C, Escape. |
 
-### Backspace Handling
+### Backspace handling
 
 `removeChar()` cascades through three layers and tells you what it removed:
 
 | Return | Source | Your action |
 |--------|--------|-------------|
-| `'pending'` | Unsent text (never transmitted to PTY) | Do nothing |
-| `'flushed'` | Text already sent to PTY | Send `\x7f` backspace to PTY |
+| `'pending'` | Unsent text (never transmitted to the PTY) | Do nothing |
+| `'flushed'` | Text already sent to the PTY | Send `\x7f` to the PTY |
 | `false` | Nothing to remove | Do nothing |
 
-The cascade: pending text first, then flushed text, then auto-detect buffer text (handles tab completion). This means backspace "just works" through any combination of typed, flushed, and tab-completed text.
+The cascade order is pending text, then flushed text, then auto-detected buffer text (which is what makes backspace work after tab completion). Backspace "just works" across any combination of typed, in-flight and completed text.
 
-### Flushed Text
+### Flushed text
 
-"Flushed" = sent to PTY but echo hasn't arrived yet. Happens during tab switches and tab completion.
+"Flushed" means sent to the PTY but the echo has not arrived yet. This happens during tab switches and tab completion.
 
 | Method | Description |
 |--------|-------------|
-| `setFlushed(count, text, render?)` | Mark text as flushed. Pass `render=false` during tab-switch restore (buffer not loaded yet). |
+| `setFlushed(count, text, render?)` | Mark text as flushed. Pass `render=false` during tab-switch restore, when the buffer is not loaded yet. |
 | `getFlushed()` | Returns `{ count, text }`. |
-| `clearFlushed()` | Clear flushed state when server echo arrives. |
+| `clearFlushed()` | Clear flushed state once the server echo arrives. |
 
-### Buffer Detection
+### Buffer detection
 
-Scan the terminal for text that exists after the prompt but wasn't typed through the overlay.
+Finds text that exists after the prompt but was never typed through the overlay.
 
 | Method | Description |
 |--------|-------------|
-| `detectBufferText()` | Scan and return detected text (or `null`). Sets it as flushed. Guarded: runs once per `clear()` cycle. |
+| `detectBufferText()` | Scan and return the detected text (or `null`), marking it flushed. Guarded: runs once per `clear()` cycle. |
 | `resetBufferDetection()` | Re-enable detection. |
-| `suppressBufferDetection()` | Block detection until next `clear()`. Use for sessions with UI framework text after the prompt. |
-| `undoDetection()` | Undo last detection — clears flushed state, re-enables detection. For tab completion retry. |
+| `suppressBufferDetection()` | Block detection until the next `clear()`. Use for sessions that render UI framework text after the prompt. |
+| `undoDetection()` | Undo the last detection: clears flushed state and re-enables detection. For tab-completion retries. |
 
 ### Rendering
 
 | Method | Description |
 |--------|-------------|
-| `rerender()` | Force re-render. Call after buffer reloads, screen redraws, resizes, reconnects. |
-| `refreshFont()` | Re-cache font properties from terminal. Call after font size or theme changes. |
+| `rerender()` | Force a re-render. Call after buffer reloads, screen redraws, resizes and reconnects. |
+| `refreshFont()` | Re-cache font and color properties from the terminal. Call after a font size or theme change. |
 
-### Prompt Utilities
+### Prompt
 
 | Method | Description |
 |--------|-------------|
-| `findPrompt()` | Find prompt position. Returns `{ row, col }` or `null`. |
-| `readPromptText()` | Read text after prompt marker. Returns string or `null`. |
+| `setPrompt(finder)` | Replace the prompt detection strategy at runtime. |
+| `findPrompt()` | Find the prompt position. Returns `{ row, col }` or `null`. |
+| `readPromptText()` | Read the text after the prompt marker. Returns a string or `null`. |
 
 ### State
 
 | Property | Type | Description |
 |----------|------|-------------|
 | `pendingText` | `string` | Unacknowledged text (read-only) |
-| `hasPending` | `boolean` | `true` if overlay has any content |
-| `state` | `ZerolagInputState` | Full snapshot: pendingText, flushedLength, flushedText, visible, promptPosition |
+| `hasPending` | `boolean` | `true` if the overlay has any content |
+| `state` | `ZerolagInputState` | Full snapshot: `pendingText`, `flushedLength`, `flushedText`, `visible`, `promptPosition` |
 
 ### Options
 
@@ -228,23 +258,23 @@ Scan the terminal for text that exists after the prompt but wasn't typed through
 {
   prompt?: PromptFinder,       // Default: { type: 'character', char: '>', offset: 2 }
   zIndex?: number,             // Default: 7
-  backgroundColor?: string,    // Default: from terminal theme
-  foregroundColor?: string,    // Default: from computed .xterm-rows style
+  backgroundColor?: string,    // Default: terminal theme background ('transparent' to disable)
+  foregroundColor?: string,    // Default: terminal theme / computed .xterm-rows style
   showCursor?: boolean,        // Default: true
-  cursorColor?: string,        // Default: from terminal theme
+  cursorColor?: string,        // Default: terminal theme cursor
   scrollDebounceMs?: number,   // Default: 50
 }
 ```
 
 ---
 
-## Integration Patterns
+## Integration patterns
 
-### Buffered Input (hold until Enter)
+### Buffered input (hold until Enter)
 
-The quick start example above. Characters accumulate in the overlay and are sent on Enter. Best for remote shells where you want to batch input.
+The quick start above. Characters accumulate in the overlay and go out on Enter. Best for remote shells where you want to batch input.
 
-### Char-at-a-Time (send immediately)
+### Char-at-a-time (send immediately)
 
 ```typescript
 terminal.onData((data) => {
@@ -256,12 +286,14 @@ terminal.onData((data) => {
     ws.send(data);
   } else if (data.length === 1 && data.charCodeAt(0) >= 32) {
     zerolag.addChar(data);
-    ws.send(data); // send immediately — overlay shows while echo travels back
+    ws.send(data); // overlay shows the char while the echo travels back
   }
 });
 ```
 
-### Tab Switching (multi-session)
+This is the mode that keeps shell features intact: tab completion, `Ctrl+R` history search, and readline bindings all still work, because every byte still reaches the PTY.
+
+### Tab switching (multi-session)
 
 ```typescript
 function switchToSession(newId: string) {
@@ -280,19 +312,19 @@ function switchToSession(newId: string) {
   const saved = savedState.get(newId);
   if (saved) zerolag.setFlushed(saved.count, saved.text, false); // silent
 
-  // Render after buffer loads
+  // Render after the buffer loads
   terminal.write('', () => zerolag.rerender());
 }
 ```
 
-### Tab Completion
+### Tab completion
 
 ```typescript
 const baseline = zerolag.readPromptText();
 zerolag.clear();
 sendToPty('\t');
 
-// After response:
+// After the response:
 zerolag.resetBufferDetection();
 const detected = zerolag.detectBufferText();
 if (detected && detected !== baseline) {
@@ -302,7 +334,7 @@ if (detected && detected !== baseline) {
 }
 ```
 
-### Resize / Font / Reconnect
+### Resize, font, reconnect
 
 ```typescript
 fitAddon.fit();
@@ -311,14 +343,31 @@ zerolag.rerender();
 terminal.options.fontSize = 18;
 zerolag.refreshFont();
 
-function onReconnect() { zerolag.rerender(); }
+function onReconnect() {
+  zerolag.rerender();
+}
 ```
 
+### Wide characters (CJK, emoji)
+
+Wide characters work out of the box: the overlay measures each character's cell width, renders double-width spans for wide ones, and positions later characters by visual column instead of character index. Line wrapping is computed in columns too, so a wrapped Japanese or Chinese line lands on the same cells the server will use.
+
+For exact Unicode 11+ widths, load xterm's Unicode addon and the overlay will defer to it:
+
+```typescript
+import { Unicode11Addon } from '@xterm/addon-unicode11';
+
+terminal.loadAddon(new Unicode11Addon());
+terminal.unicode.activeVersion = '11';
+```
+
+Without it, a built-in range table covers Hangul, Kana, CJK Unified (including Ext A through G), fullwidth forms and the emoji planes.
+
 ---
 
-## How It Works
+## How it works
 
-### DOM Structure
+### DOM structure
 
 ```
 div.xterm-screen (position: relative)
@@ -326,53 +375,61 @@ div.xterm-screen (position: relative)
   ├── div.xterm-selection (z-index: 1)
   ├── div.xterm-helpers (z-index: 5)
   ├── div.xterm-decoration-container (z-index: 6-7)
-  └── div[zerolag overlay] (z-index: 7)  ← our overlay (invisible to Ink)
+  └── div[zerolag overlay] (z-index: 7)  ← our overlay, invisible to Ink
 ```
 
-### Per-Character Grid Alignment
+### Per-character grid alignment
 
 Each character is an absolutely-positioned `<span>`:
 
 ```
-left  = charIndex * cellWidth   (CSS pixels)
-top   = lineIndex * cellHeight  (CSS pixels)
-width = cellWidth               (exact cell width)
+left  = visualColumn * cellWidth   (CSS pixels)
+top   = lineIndex    * cellHeight  (CSS pixels)
+width = cellWidth * charCellWidth  (1 cell, or 2 for wide characters)
 ```
 
-This avoids sub-pixel drift from normal DOM text flow.
+Positioning by visual column instead of letting the browser lay out text is what removes sub-pixel drift.
 
-### Font Matching
+### Font matching
 
 1. `fontFamily`, `fontSize`, `fontWeight` from `terminal.options`
-2. `letterSpacing` from computed style of `.xterm-rows`
-3. `-webkit-font-smoothing: antialiased` (matches canvas grayscale)
+2. `letterSpacing` from the computed style of `.xterm-rows`
+3. `-webkit-font-smoothing: antialiased` (matches canvas grayscale AA)
 4. `font-feature-settings: 'liga' 0, 'calt' 0` (no ligatures)
 5. `text-rendering: geometricPrecision`
 
-### Cell Dimensions
+### Cell dimensions
 
 - **xterm.js v5.x**: `terminal._core._renderService.dimensions.css.cell` (private API)
 - **xterm.js v7+**: `terminal.dimensions.css.cell` (public API, auto-detected)
 
-### Prompt Column Locking
+### Prompt column locking
 
-When flushed text exists, the prompt column is locked to prevent jitter from full-screen redraws. Row changes are allowed (output can scroll the prompt).
+While flushed text exists the prompt column is locked, so a full-screen redraw cannot make the overlay jitter sideways. Row changes are still allowed, because output legitimately scrolls the prompt.
 
-### Scroll Awareness
+### Scroll awareness
 
-Overlay hides when scrolled up (`viewportY !== baseY`). Debounced re-render when scrolling back to bottom.
+The overlay hides when the viewport is scrolled up (`viewportY !== baseY`) and re-renders, debounced, when you scroll back to the bottom.
 
 ---
 
-## Known Limitations
+## Known limitations
 
-- **Canvas/WebGL font mismatch**: Minor sub-pixel differences possible. Per-character absolute positioning minimizes this.
-- **Unicode/emoji**: Multi-byte characters occupy variable cell widths — rendered at single-cell width, causing misalignment.
-- **Password prompts**: Overlay shows characters that aren't echoed. Call `clear()` when you detect no-echo mode.
-- **Prompt in output**: If `$` appears in command output, prompt detection may find the wrong position. Use regex or custom finder.
+- **Canvas and WebGL font mismatch**: minor sub-pixel differences are still possible. Per-character absolute positioning keeps them small.
+- **Grapheme clusters**: widths are summed per code point, so ZWJ emoji sequences (for example 👨‍👩‍👧) and combining marks can be over-counted. Single-code-point emoji and CJK are correct.
+- **Password prompts**: the overlay will happily show characters the server is not echoing. Call `clear()` when you detect a no-echo prompt.
+- **Prompt characters in output**: if your prompt marker also appears in command output, detection can latch onto the wrong line. Use a regex or a custom finder.
 
 ---
 
+## Origin
+
+[Codeman](https://getcodeman.com) needed this before anyone else did. A coding agent you drive from your phone over a tunnel is unusable if every keystroke costs a round trip.
+
+So the overlay was built there, ran in production for thousands of hours, and survived three deep code audits before being pulled out into this standalone library with its tests intact. Nothing was reimplemented for the extraction: the engine here is the one Codeman ships.
+
+Want the whole thing? [**getcodeman.com**](https://getcodeman.com) · [github.com/Ark0N/Codeman](https://github.com/Ark0N/Codeman)
+
 ## License
 
-MIT — [Codeman](https://github.com/Ark0N/Codeman) Contributors
+MIT, [Codeman](https://github.com/Ark0N/Codeman) Contributors

packages/xterm-zerolag-input/package.json

@@ -1,7 +1,7 @@
 {
   "name": "xterm-zerolag-input",
-  "version": "0.1.4",
-  "description": "Instant keystroke feedback overlay for xterm.js — eliminates perceived input latency over high-RTT connections",
+  "version": "0.1.8",
+  "description": "Instant keystroke feedback overlay for xterm.js: Mosh-inspired local echo that removes perceived input latency over SSH, tunnels and other high-RTT connections",
   "type": "module",
   "main": "dist/index.cjs",
   "module": "dist/index.js",
@@ -26,8 +26,16 @@
     "xterm",
     "xterm.js",
     "terminal",
+    "web-terminal",
     "local-echo",
+    "local echo",
+    "mosh",
     "input-latency",
+    "latency",
+    "zero-lag",
+    "keystroke",
+    "ssh",
+    "remote-terminal",
     "overlay",
     "addon"
   ],

scripts/build.mjs

@@ -67,6 +67,7 @@ appendFileSync(
 
 // 4. Minify frontend assets
 run('minify input-cjk.js', 'npx esbuild dist/web/public/input-cjk.js --minify --outfile=dist/web/public/input-cjk.js --allow-overwrite');
+run('minify i18n.js', 'npx esbuild dist/web/public/i18n.js --minify --outfile=dist/web/public/i18n.js --allow-overwrite');
 run('minify sanitize-html.js', 'npx esbuild dist/web/public/sanitize-html.js --minify --outfile=dist/web/public/sanitize-html.js --allow-overwrite');
 run('minify app.js', 'npx esbuild dist/web/public/app.js --minify --outfile=dist/web/public/app.js --allow-overwrite');
 run('minify terminal-ui.js', 'npx esbuild dist/web/public/terminal-ui.js --minify --outfile=dist/web/public/terminal-ui.js --allow-overwrite');
@@ -86,6 +87,7 @@ console.log('\n[build] content-hash cache busting');
     'styles.css',
     'mobile.css',
     'constants.js',
+    'i18n.js',
     'mobile-handlers.js',
     'voice-input.js',
     'notification-manager.js',

scripts/capture-readme-gifs.mjs

@@ -0,0 +1,482 @@
+#!/usr/bin/env node
+
+/**
+ * capture-readme-gifs.mjs
+ *
+ * Deterministic README GIFs — no real server, Claude CLI, or tmux. Reuses the
+ * mock-injection pipeline from capture-readme-screenshots.mjs (static file
+ * server + page.route mocks), drives a scripted timeline in the page, records
+ * it with Playwright video, and converts to GIF via ffmpeg palette encoding.
+ *
+ * Scenes:
+ *   1. subagent-demo.gif  — terminal spawns 3 parallel agents; floating agent
+ *      windows open one by one and stream tool-call activity live (driven
+ *      through the real _onSubagentDiscovered/_onSubagentToolCall handlers).
+ *   2. zerolag-demo.gif   — side-by-side typing: instant local echo (zerolag)
+ *      vs bursty ~350 ms server echo, rendered with the vendored xterm.
+ *
+ * Usage:  node scripts/capture-readme-gifs.mjs
+ *         SCREENSHOT_OUT_DIR=/path/to/review node scripts/capture-readme-gifs.mjs
+ * Output: docs/images/ (or flat into SCREENSHOT_OUT_DIR)
+ * Requires: ffmpeg
+ */
+
+import { chromium } from 'playwright';
+import { execSync } from 'child_process';
+import { mkdtempSync, rmSync } from 'fs';
+import { tmpdir } from 'os';
+import { join } from 'path';
+import {
+  PORT,
+  SESSION_IDS,
+  STANDARD_SESSIONS,
+  buildInitPayload,
+  startStaticServer,
+  setupRoutes,
+  injectState,
+  outPath,
+  RST, GRN, YEL, MAG, CYN, GRY, BOLD,
+} from './capture-readme-screenshots.mjs';
+
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+
+const GIF_COLORS = 192;
+
+// ─── ffmpeg conversion (palette recipe from capture-subagent-gif.mjs) ────────
+
+function webmToGif(videoPath, gifPath, { ss, duration, width, fps }) {
+  // One GLOBAL palette (default stats_mode=full) + ordered dither: per-frame
+  // palettes (stats_mode=single:new=1) make dirty rectangles visibly mismatch
+  // on flat dark UI, and error-diffusion dither shimmers between frames.
+  const filters = `fps=${fps},scale=${width}:-1:flags=lanczos`;
+  execSync(
+    `ffmpeg -y -loglevel error -ss ${ss.toFixed(2)} -t ${duration} -i "${videoPath}" ` +
+      `-vf "${filters},split[s0][s1];[s0]palettegen=max_colors=${GIF_COLORS}:reserve_transparent=0[p];` +
+      `[s1][p]paletteuse=dither=bayer:bayer_scale=5:diff_mode=rectangle" "${gifPath}"`,
+    { stdio: 'inherit' }
+  );
+}
+
+// ─── Scene 1: subagent demo ──────────────────────────────────────────────────
+
+const SUBAGENT_VIEWPORT = { width: 1440, height: 810 };
+
+// Terminal content visible before the agents spawn
+const TERMINAL_PRESPAWN = [
+  '',
+  `${GRN}●${RST} Working on ${CYN}/home/arkon/codeman-cases/testcase${RST} - I'll use the ${BOLD}Task tool${RST} to spawn parallel agents.`,
+  '',
+  `${GRN}●${RST} ${BOLD}Read${RST}(/home/arkon/codeman-cases/testcase/CLAUDE.md)`,
+  `  ${GRY}░${RST} Read ${BOLD}127${RST} lines ${GRY}│${RST} ${CYN}1.2KB${RST}`,
+  '',
+  `${GRN}●${RST} ${BOLD}Bash${RST}(find . -name "*.ts" -not -path "*/node_modules/*" | head -20)`,
+  `  ${GRY}░${RST} ./src/index.ts`,
+  `  ${GRY}░${RST} ./src/session.ts`,
+  `  ${GRY}░${RST} ./src/web/server.ts`,
+  `  ${GRY}░${RST} ${GRY}... (17 more)${RST}`,
+  '',
+  `${GRN}●${RST} I'll spawn 3 parallel research agents to analyze different parts of the codebase simultaneously.`,
+  '',
+].join('\r\n');
+
+function makeAgent(agentId, description, startedOffsetMs) {
+  return {
+    agentId,
+    sessionId: 'claude-sess-w1-0001',
+    projectHash: 'abc123',
+    filePath: `/tmp/${agentId}.jsonl`,
+    startedAt: new Date(Date.now() - startedOffsetMs).toISOString(),
+    lastActivityAt: Date.now(),
+    status: 'active',
+    toolCallCount: 0,
+    entryCount: 0,
+    fileSize: 4000,
+    description,
+    model: 'claude-haiku-4-5-20251001',
+    modelShort: 'haiku',
+    totalInputTokens: 0,
+    totalOutputTokens: 0,
+    parentSessionId: SESSION_IDS.w1,
+  };
+}
+
+// Timeline events: t (ms from scene start) + kind
+//   term     — write raw data to the session terminal
+//   discover — register subagent + open + position its floating window
+//   tool     — stream a tool call into an agent window
+//   msg      — stream an assistant message into an agent window
+//   complete — flip an agent to completed
+function buildSubagentTimeline() {
+  const T = (lines) => lines.join('\r\n') + '\r\n';
+  const tool = (t, agentId, name, input) => ({ t, kind: 'tool', agentId, tool: name, input });
+  const msg = (t, agentId, text) => ({ t, kind: 'msg', agentId, text });
+
+  return [
+    {
+      t: 600,
+      kind: 'term',
+      data: T([
+        `${GRN}●${RST} ${BOLD}Task${RST}(Find and document all API endpoints in src/)`,
+        `  ${GRY}░${RST} Spawned ${CYN}agent-001${RST} ${GRY}(haiku)${RST}`,
+        '',
+      ]),
+    },
+    {
+      t: 1000,
+      kind: 'discover',
+      agent: makeAgent('agent-001', 'Find and document all API endpoints in src/', 2000),
+      x: 440, y: 45,
+    },
+    tool(1500, 'agent-001', 'Glob', { pattern: 'src/**/*.ts' }),
+    {
+      t: 2000,
+      kind: 'term',
+      data: T([
+        `${GRN}●${RST} ${BOLD}Task${RST}(Explore and understand test structure in test/)`,
+        `  ${GRY}░${RST} Spawned ${CYN}agent-002${RST} ${GRY}(haiku)${RST}`,
+        '',
+      ]),
+    },
+    tool(2200, 'agent-001', 'Read', { file_path: '/home/arkon/codeman/src/web/server.ts' }),
+    {
+      t: 2500,
+      kind: 'discover',
+      agent: makeAgent('agent-002', 'Explore and understand test structure in test/', 1200),
+      x: 880, y: 45,
+    },
+    tool(3000, 'agent-002', 'Glob', { pattern: 'test/**/*.test.ts' }),
+    {
+      t: 3300,
+      kind: 'term',
+      data: T([
+        `${GRN}●${RST} ${BOLD}Task${RST}(Analyze TypeScript type definitions in src/types.ts)`,
+        `  ${GRY}░${RST} Spawned ${CYN}agent-003${RST} ${GRY}(haiku)${RST}`,
+        '',
+      ]),
+    },
+    tool(3500, 'agent-001', 'Grep', { pattern: 'app\\.get|app\\.post|app\\.delete', path: 'src/' }),
+    {
+      t: 3800,
+      kind: 'discover',
+      agent: makeAgent('agent-003', 'Analyze TypeScript type definitions in src/types.ts', 400),
+      x: 660, y: 400,
+    },
+    tool(4100, 'agent-002', 'Read', { file_path: '/home/arkon/codeman/test/respawn-test-utils.ts' }),
+    {
+      t: 4500,
+      kind: 'term',
+      data: T([
+        `${MAG}✻${RST} ${YEL}Waiting for agents...${RST} ${GRY}(${BOLD}esc${RST}${GRY} to interrupt · 32s · ↓ 1.7k tokens · thinking)${RST}`,
+        '',
+      ]),
+    },
+    tool(4700, 'agent-003', 'Read', { file_path: '/home/arkon/codeman/src/types.ts' }),
+    tool(5200, 'agent-001', 'Read', { file_path: '/home/arkon/codeman/src/web/schemas.ts' }),
+    tool(5600, 'agent-002', 'Read', { file_path: '/home/arkon/codeman/config/vitest.config.ts' }),
+    tool(6100, 'agent-003', 'Grep', { pattern: 'export (interface|type)', path: 'src/types/' }),
+    msg(6700, 'agent-001', 'Found 47 API endpoints across server.ts. Documenting REST paths...'),
+    tool(7100, 'agent-002', 'Grep', { pattern: 'const PORT =', path: 'test/' }),
+    msg(7700, 'agent-002', 'Analyzing test patterns: MockSession, unique ports, fileParallelism: false...'),
+    tool(8100, 'agent-003', 'Read', { file_path: '/home/arkon/codeman/src/types/index.ts' }),
+    msg(8700, 'agent-003', 'Mapped 38 exported interfaces across 15 domain files. Building summary...'),
+    {
+      t: 9300,
+      kind: 'term',
+      data: T([
+        `${GRN}●${RST} ${CYN}agent-001${RST}: ${GRY}12 tool calls — Glob, Read(server.ts), Grep(endpoints)...${RST}`,
+        `${GRN}●${RST} ${CYN}agent-002${RST}: ${GRY}8 tool calls — Glob, Read(test-utils), Read(vitest.config)...${RST}`,
+        `${GRN}●${RST} ${CYN}agent-003${RST}: ${GRY}7 tool calls — Read(types.ts), Grep(interface)...${RST}`,
+        '',
+      ]),
+    },
+    tool(10100, 'agent-001', 'Glob', { pattern: 'src/web/routes/*.ts' }),
+    tool(10600, 'agent-002', 'Read', { file_path: '/home/arkon/codeman/test/setup.ts' }),
+    tool(11100, 'agent-003', 'Grep', { pattern: 'assertNever', path: 'src/' }),
+    {
+      t: 11600,
+      kind: 'term',
+      data: T([`${GRN}●${RST} ${GRY}171.8k, 13s${RST} ${GRY}│${RST} ${GRY}1.7k tokens${RST} ${GRY}│${RST} ${GRY}thinking${RST}`, '']),
+    },
+  ];
+}
+
+const SUBAGENT_TAIL_HOLD = 2500; // hold the final frame
+
+async function recordSubagentScene(browser, videoDir) {
+  console.log('\n1/2 Recording subagent-demo...');
+
+  const context = await browser.newContext({
+    viewport: SUBAGENT_VIEWPORT,
+    deviceScaleFactor: 1,
+    recordVideo: { dir: videoDir, size: SUBAGENT_VIEWPORT },
+  });
+  const recStart = Date.now();
+  const page = await context.newPage();
+  page.setDefaultTimeout(30000);
+
+  // Start with NO subagents — they appear during the recording
+  const initPayload = buildInitPayload(STANDARD_SESSIONS);
+  await setupRoutes(page, initPayload, TERMINAL_PRESPAWN);
+  await page.goto(`http://localhost:${PORT}`, { waitUntil: 'domcontentloaded' });
+  await injectState(page, initPayload, TERMINAL_PRESPAWN, SESSION_IDS.w1);
+
+  await page.evaluate(() => {
+    try { window.app?.fitAddon?.fit(); } catch {}
+    window.app?.terminal?.scrollToBottom();
+  });
+  await sleep(500);
+
+  const timeline = buildSubagentTimeline();
+  const totalMs = Math.max(...timeline.map((e) => e.t)) + SUBAGENT_TAIL_HOLD;
+  const sceneStart = Date.now();
+
+  // Run the whole timeline inside the page so events interleave naturally
+  await page.evaluate((events) => {
+    const app = window.app;
+    for (const ev of events) {
+      setTimeout(() => {
+        try {
+          if (ev.kind === 'term') {
+            app.terminal.write(ev.data);
+            app.terminal.scrollToBottom();
+          } else if (ev.kind === 'discover') {
+            app._onSubagentDiscovered(ev.agent);
+            app.openSubagentWindow(ev.agent.agentId);
+            // The spawn animation (400ms) lands on the auto-grid; glide to our tile after it
+            setTimeout(() => {
+              const win = app.subagentWindows.get(ev.agent.agentId);
+              if (win?.element) {
+                win.element.style.transition = 'left 0.25s ease, top 0.25s ease';
+                win.element.style.left = `${ev.x}px`;
+                win.element.style.top = `${ev.y}px`;
+              }
+            }, 520);
+            setTimeout(() => {
+              const win = app.subagentWindows.get(ev.agent.agentId);
+              if (win?.element) win.element.style.transition = '';
+              app.updateConnectionLines();
+            }, 850);
+          } else if (ev.kind === 'tool') {
+            app._onSubagentToolCall({
+              agentId: ev.agentId,
+              tool: ev.tool,
+              input: ev.input,
+              timestamp: new Date().toISOString(),
+            });
+          } else if (ev.kind === 'msg') {
+            app._onSubagentMessage({
+              agentId: ev.agentId,
+              role: 'assistant',
+              text: ev.text,
+              timestamp: new Date().toISOString(),
+            });
+          } else if (ev.kind === 'complete') {
+            app._onSubagentCompleted({ agentId: ev.agentId, timestamp: new Date().toISOString() });
+          }
+        } catch (err) {
+          console.error('timeline event failed', ev, err);
+        }
+      }, ev.t);
+    }
+  }, timeline);
+
+  await sleep(totalMs + 500);
+
+  await page.close();
+  const videoPath = await page.video().path();
+  await context.close();
+
+  return {
+    videoPath,
+    ss: (sceneStart - recStart) / 1000 - 0.4,
+    duration: (totalMs + 400) / 1000,
+  };
+}
+
+// ─── Scene 2: zerolag typing comparison ──────────────────────────────────────
+
+const ZEROLAG_VIEWPORT = { width: 1280, height: 470 };
+const TYPED_TEXT = 'echo "zero lag typing from anywhere"';
+const TYPE_INTERVAL_MS = 110;
+const REMOTE_FLUSH_MS = 350; // server-echo pane flushes queued chars in bursts
+const ZEROLAG_TAIL_HOLD = 1800;
+
+const ZEROLAG_HTML = `<!DOCTYPE html>
+<html>
+<head>
+<link rel="stylesheet" href="http://localhost:${PORT}/vendor/xterm.css">
+<script src="http://localhost:${PORT}/vendor/xterm.min.js"></script>
+<style>
+  * { margin: 0; box-sizing: border-box; }
+  body {
+    width: 1280px; height: 470px; background: #0a0a0c;
+    display: flex; align-items: center; justify-content: center; gap: 48px;
+    font-family: -apple-system, 'Segoe UI', Roboto, sans-serif;
+  }
+  .pane { width: 560px; }
+  .card {
+    background: #131316; border: 1px solid rgba(255,255,255,0.08);
+    border-radius: 10px; overflow: hidden;
+    box-shadow: 0 8px 32px rgba(0,0,0,0.45);
+  }
+  .card-head {
+    display: flex; align-items: baseline; gap: 10px;
+    padding: 12px 16px; border-bottom: 1px solid rgba(255,255,255,0.06);
+  }
+  .dot { width: 9px; height: 9px; border-radius: 50%; align-self: center; }
+  .title { font-size: 15px; font-weight: 600; color: #e8e8ea; }
+  .sub { font-size: 12.5px; color: #8b8b92; }
+  .term { padding: 16px 8px 12px 16px; height: 165px; }
+  .good .dot { background: #22c55e; box-shadow: 0 0 8px rgba(34,197,94,0.7); }
+  .bad  .dot { background: #ef4444; box-shadow: 0 0 8px rgba(239,68,68,0.7); }
+  .tag {
+    margin-top: 14px; text-align: center; font-size: 14.5px; color: #7e7e86;
+  }
+  .tag b { color: #22c55e; font-weight: 600; }
+  .bad-tag b { color: #ef4444; }
+</style>
+</head>
+<body>
+  <div class="pane">
+    <div class="card good">
+      <div class="card-head">
+        <span class="dot"></span>
+        <span class="title">With zerolag-input</span>
+        <span class="sub">instant local echo</span>
+      </div>
+      <div class="term" id="termLeft"></div>
+    </div>
+    <div class="tag">keystrokes echo in <b>0 ms</b></div>
+  </div>
+  <div class="pane">
+    <div class="card bad">
+      <div class="card-head">
+        <span class="dot"></span>
+        <span class="title">Without</span>
+        <span class="sub">server round-trip echo</span>
+      </div>
+      <div class="term" id="termRight"></div>
+    </div>
+    <div class="tag bad-tag">keystrokes echo after <b>~350 ms</b></div>
+  </div>
+</body>
+</html>`;
+
+async function recordZerolagScene(browser, videoDir) {
+  console.log('\n2/2 Recording zerolag-demo...');
+
+  const context = await browser.newContext({
+    viewport: ZEROLAG_VIEWPORT,
+    deviceScaleFactor: 1,
+    recordVideo: { dir: videoDir, size: ZEROLAG_VIEWPORT },
+  });
+  const recStart = Date.now();
+  const page = await context.newPage();
+  page.setDefaultTimeout(30000);
+
+  await page.setContent(ZEROLAG_HTML, { waitUntil: 'load' });
+  await page.waitForFunction(() => typeof Terminal !== 'undefined');
+
+  await page.evaluate(() => {
+    const theme = {
+      background: '#131316',
+      foreground: '#e8e8ea',
+      cursor: '#22c55e',
+      cursorAccent: '#131316',
+    };
+    const mk = (id) => {
+      const term = new Terminal({
+        cols: 44,
+        rows: 5,
+        fontSize: 20,
+        fontFamily: "'SF Mono', 'Cascadia Code', Menlo, monospace",
+        cursorBlink: true,
+        cursorStyle: 'block',
+        theme,
+      });
+      term.open(document.getElementById(id));
+      term.write('\x1b[32m❯\x1b[0m ');
+      return term;
+    };
+    window.termLeft = mk('termLeft');
+    window.termRight = mk('termRight');
+  });
+  await sleep(600);
+
+  const sceneStart = Date.now();
+  const typingMs = TYPED_TEXT.length * TYPE_INTERVAL_MS;
+  const totalMs = typingMs + REMOTE_FLUSH_MS + ZEROLAG_TAIL_HOLD;
+
+  await page.evaluate(
+    ({ text, interval, flushEvery }) => {
+      let i = 0;
+      const remoteQueue = [];
+      const typer = setInterval(() => {
+        if (i >= text.length) { clearInterval(typer); return; }
+        const ch = text[i++];
+        window.termLeft.write(ch); // local echo: instant
+        remoteQueue.push(ch); // server echo: waits for the round-trip
+      }, interval);
+      const flusher = setInterval(() => {
+        if (remoteQueue.length) window.termRight.write(remoteQueue.splice(0).join(''));
+        if (i >= text.length && remoteQueue.length === 0) clearInterval(flusher);
+      }, flushEvery);
+    },
+    { text: TYPED_TEXT, interval: TYPE_INTERVAL_MS, flushEvery: REMOTE_FLUSH_MS }
+  );
+
+  await sleep(totalMs + 400);
+
+  await page.close();
+  const videoPath = await page.video().path();
+  await context.close();
+
+  return {
+    videoPath,
+    ss: (sceneStart - recStart) / 1000 - 0.6, // small lead-in with idle cursors
+    duration: (totalMs + 600) / 1000,
+  };
+}
+
+// ─── Main ────────────────────────────────────────────────────────────────────
+
+async function main() {
+  console.log('='.repeat(60));
+  console.log('Codeman README GIF Capture');
+  console.log('='.repeat(60));
+
+  const server = await startStaticServer();
+  const videoDir = mkdtempSync(join(tmpdir(), 'codeman-gifs-'));
+  let browser;
+
+  try {
+    browser = await chromium.launch({
+      headless: true,
+      args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage', '--disable-gpu'],
+    });
+
+    const sub = await recordSubagentScene(browser, videoDir);
+    const subGif = outPath('images', 'subagent-demo.gif');
+    webmToGif(sub.videoPath, subGif, { ss: Math.max(0, sub.ss), duration: sub.duration, width: 960, fps: 8 });
+    console.log(`  Saved: ${subGif}`);
+
+    const zl = await recordZerolagScene(browser, videoDir);
+    const zlGif = outPath('images', 'zerolag-demo.gif');
+    webmToGif(zl.videoPath, zlGif, { ss: Math.max(0, zl.ss), duration: zl.duration, width: 900, fps: 10 });
+    console.log(`  Saved: ${zlGif}`);
+
+    console.log('\nDone.');
+  } catch (err) {
+    console.error('\nFatal error:', err.message);
+    console.error(err.stack);
+    process.exitCode = 1;
+  } finally {
+    if (browser) await browser.close().catch(() => {});
+    server.close();
+    rmSync(videoDir, { recursive: true, force: true });
+  }
+}
+
+process.on('SIGINT', () => process.exit(1));
+
+main();

scripts/capture-readme-real.mjs

@@ -50,7 +50,10 @@ async function newCtx(browser) {
       try {
         localStorage.setItem('codeman:skin', skin);
         localStorage.setItem('codeman-font-size', String(font));
-        const blob = { skin, showFileBrowser: false, showProjectInsights: false };
+        const blob = { skin, showFileBrowser: false, showProjectInsights: false, showTokenCount: false };
+        // Don't auto-hide subagent windows that belong to a non-active tab — the
+        // subagent scene re-homes agents and needs both windows visible at once.
+        blob.subagentActiveTabOnly = false;
         if (planUsage) blob.showPlanUsageLimits = true;
         localStorage.setItem('codeman-app-settings', JSON.stringify(blob));
       } catch {
@@ -136,9 +139,9 @@ async function sceneSubagent(browser) {
   const sessions = await listSessions(page);
   const targetId = process.env.SUBAGENT_SID || (sessions.find((s) => s.mode === 'claude') || sessions[0])?.id;
   if (targetId) await page.evaluate((id) => window.app.selectSession(id), targetId);
-  // Wait (up to ~25s) for live subagents to arrive via SSE into app.subagents.
+  // Wait (up to ~45s) for live subagents to arrive via SSE into app.subagents.
   let agents = [];
-  for (let i = 0; i < 25; i++) {
+  for (let i = 0; i < 45; i++) {
     agents = await page.evaluate(() =>
       Array.from(window.app.subagents?.entries?.() || []).map(([id, a]) => ({ id, name: a.name ?? a.agentType ?? '' }))
     );
@@ -151,6 +154,44 @@ async function sceneSubagent(browser) {
     await context.close();
     return;
   }
+  // The window body renders from app.subagentActivity, which fills ONLY from live
+  // SSE tool-call/progress events — a fresh client never gets past activity replayed.
+  // So sit connected and wait for live activity to accumulate, then open the two
+  // agents that actually have content (otherwise the windows read "No activity yet").
+  let active = [];
+  for (let i = 0; i < 100; i++) {
+    active = await page.evaluate(() =>
+      Array.from(window.app.subagentActivity?.entries?.() || [])
+        .filter(([, arr]) => Array.isArray(arr) && arr.length >= 1)
+        .map(([id, arr]) => ({ id, n: arr.length }))
+        .sort((a, b) => b.n - a.n)
+    );
+    if (active.length >= 2) break;
+    // xhigh-effort agents churn in bursts between long thinking pauses, so be
+    // patient (~150s); accept a single populated window after ~45s if that's all.
+    if (i >= 30 && active.length >= 1) break;
+    await sleep(1500);
+  }
+  console.log('  agents with live activity:', JSON.stringify(active));
+  const openIds = (active.length ? active : agents).map((a) => a.id);
+  // Capture-only DOM nudge: on fresh dev sessions, a tab's claudeSessionId stays the
+  // Codeman id and never becomes the real Claude conversation UUID, so the window
+  // open-gate (claudeSessionId === agent.sessionId) + the activeTabOnly hide rule both
+  // fail. Re-home the chosen agents onto the active tab and align its claudeSessionId
+  // to the agents' (shared) sessionId so the windows open AND show their live activity.
+  await page.evaluate(
+    (ids) => {
+      const activeId = window.app.activeSessionId;
+      const tab = window.app.sessions.get(activeId);
+      ids.slice(0, 2).forEach((id) => {
+        const a = window.app.subagents.get(id);
+        if (!a) return;
+        a.parentSessionId = activeId;
+        if (tab && a.sessionId) tab.claudeSessionId = a.sessionId;
+      });
+    },
+    openIds
+  );
   await page.evaluate(
     (ids) => {
       ids.slice(0, 2).forEach((id) => {
@@ -159,22 +200,33 @@ async function sceneSubagent(browser) {
         } catch {}
       });
     },
-    agents.map((a) => a.id)
+    openIds
   );
   await sleep(2000);
   await page.evaluate(() => {
+    // Viewport-relative tiling: center two subagent windows over the terminal so
+    // the layout adapts to whatever VW/VH the capture uses (e.g. the HQ 1100×650
+    // recipe) instead of overflowing at narrower widths.
     const wins = Array.from(window.app.subagentWindows.values());
-    const place = [
-      { left: 360, top: 60, w: 430, h: 330 },
-      { left: 810, top: 60, w: 430, h: 330 },
-    ];
+    const W = window.innerWidth;
+    const H = window.innerHeight;
+    const winW = Math.min(440, Math.floor((W - 60) / 2 - 10));
+    const winH = Math.min(360, Math.floor(H * 0.56));
+    const top = Math.floor(H * 0.16);
+    const gap = 16;
+    const totalW = winW * 2 + gap;
+    const startLeft = Math.max(16, Math.floor((W - totalW) / 2));
     wins.slice(0, 2).forEach((win, i) => {
       const el = win.element;
-      const p = place[i];
-      el.style.left = p.left + 'px';
-      el.style.top = p.top + 'px';
-      el.style.width = p.w + 'px';
-      el.style.height = p.h + 'px';
+      // Force visible: a freshly opened window may be hidden by the activeTabOnly
+      // rule before we override it (we also seed subagentActiveTabOnly:false).
+      win.hidden = false;
+      win.minimized = false;
+      el.style.display = 'flex';
+      el.style.left = startLeft + i * (winW + gap) + 'px';
+      el.style.top = top + 'px';
+      el.style.width = winW + 'px';
+      el.style.height = winH + 'px';
     });
   });
   await sleep(1500);

scripts/capture-real-overview.mjs

@@ -79,6 +79,7 @@ const main = async () => {
           showMonitor: false,
           showSubagents: false,
           showProjectInsights: false,
+          showTokenCount: false,
         };
         if (planUsage) blob.showPlanUsageLimits = true;
         localStorage.setItem('codeman-app-settings', JSON.stringify(blob));

scripts/capture-subagent-gif.mjs

@@ -126,6 +126,7 @@ async function capture() {
         showMonitor: false,
         showProjectInsights: false,
         showFileBrowser: false,
+        showTokenCount: false,
       });
       localStorage.setItem('codeman-app-settings', JSON.stringify(existing));
     });
@@ -230,6 +231,7 @@ async function capture() {
         showMonitor: false,
         showProjectInsights: false,
         showFileBrowser: false,
+        showTokenCount: false,
       });
       localStorage.setItem('codeman-app-settings', JSON.stringify(existing));
     });

scripts/capture-subagent-screenshots.mjs

@@ -221,6 +221,7 @@ async function configureSettings(page) {
       subagentTrackingEnabled: true,
       subagentActiveTabOnly: false, // Show all subagents regardless of active tab
       showMonitor: true,
+      showTokenCount: false,
     };
     localStorage.setItem('codeman-app-settings', JSON.stringify(settings));
   });

scripts/fix-node-pty.mjs

@@ -0,0 +1,261 @@
+#!/usr/bin/env node
+/**
+ * @fileoverview Repairs node-pty's macOS `spawn-helper` and verifies that a PTY
+ * can really be spawned. Called by `scripts/postinstall.js` on every install and
+ * exposed as `npm run fix:node-pty` for repairing an install after the fact.
+ *
+ * Why this exists (issues #6 and #204):
+ *
+ * node-pty@1.1.0 publishes its macOS prebuilt helper as
+ * `prebuilds/darwin-<arch>/spawn-helper` with mode 0644, i.e. no execute bit.
+ * On macOS node-pty launches every PTY through that helper with posix_spawnp,
+ * which then fails EACCES and surfaces as `Error: posix_spawnp failed.` on every
+ * session start.
+ *
+ * It is macOS-exclusive twice over: `spawn-helper` is an `OS=="mac"` gyp target,
+ * and pty.cc only spawns it under `#if defined(__APPLE__)`. node-pty ships
+ * prebuilds for darwin and win32 only, so Linux always compiles from source
+ * (which produces an executable helper) and never sees the bug.
+ *
+ * The repair is a chmod, NOT a rebuild: the prebuilt binary itself is fine, and
+ * requiring a from-source rebuild would make every macOS install depend on Xcode
+ * command line tools. A rebuild is attempted only when a chmod plus a real spawn
+ * probe still can't get a working PTY, and the prebuilds tree is backed up first
+ * so a failed rebuild can never leave the install worse than it started.
+ */
+
+import { chmodSync, cpSync, existsSync, readdirSync, rmSync, statSync } from 'node:fs';
+import { execSync } from 'node:child_process';
+import { createRequire } from 'node:module';
+import { tmpdir } from 'node:os';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const require = createRequire(import.meta.url);
+
+/** Errors that mean "the native module or its helper is unusable", i.e. worth a rebuild. */
+const NATIVE_FAILURE_PATTERN = /posix_spawnp|spawn-helper|Failed to load native module|Cannot find module/i;
+
+/**
+ * Locates the installed node-pty package directory.
+ *
+ * @returns {string|null} Absolute path to the package root, or null if not installed.
+ */
+export function findNodePtyDir() {
+    // package.json first: node-pty declares no "exports" map, so the subpath resolves,
+    // and it lands on the package root directly. require.resolve('node-pty') would give
+    // <pkg>/lib/index.js, which is one directory deeper than callers expect.
+    try {
+        return dirname(require.resolve('node-pty/package.json'));
+    } catch {
+        /* fall through */
+    }
+    try {
+        return join(dirname(require.resolve('node-pty')), '..');
+    } catch {
+        return null;
+    }
+}
+
+/**
+ * Lists every `spawn-helper` shipped in a node-pty install.
+ *
+ * node-pty's own loader (lib/utils.js) checks `build/Release`, `build/Debug` and
+ * then `prebuilds/<platform>-<arch>`, and takes the helper from whichever
+ * directory the native module loaded out of, so all of them must be executable,
+ * not just the one this machine happens to use today.
+ *
+ * @param {string} ptyDir Absolute path to the node-pty package root.
+ * @returns {string[]} Absolute paths of the helpers that exist on disk.
+ */
+export function listSpawnHelpers(ptyDir) {
+    const dirs = [join(ptyDir, 'build', 'Release'), join(ptyDir, 'build', 'Debug')];
+
+    const prebuilds = join(ptyDir, 'prebuilds');
+    if (existsSync(prebuilds)) {
+        try {
+            for (const entry of readdirSync(prebuilds, { withFileTypes: true })) {
+                if (entry.isDirectory()) dirs.push(join(prebuilds, entry.name));
+            }
+        } catch {
+            /* unreadable prebuilds dir: nothing to repair there */
+        }
+    }
+
+    return dirs.map((d) => join(d, 'spawn-helper')).filter((p) => existsSync(p));
+}
+
+/**
+ * Adds the execute bit to every `spawn-helper` that is missing it.
+ *
+ * @param {string} ptyDir Absolute path to the node-pty package root.
+ * @returns {{ repaired: string[], failed: Array<{ path: string, error: string }> }}
+ */
+export function repairSpawnHelpers(ptyDir) {
+    const repaired = [];
+    const failed = [];
+
+    for (const helper of listSpawnHelpers(ptyDir)) {
+        try {
+            const mode = statSync(helper).mode & 0o777;
+            if ((mode & 0o111) === 0o111) continue; // already executable by all
+            chmodSync(helper, mode | 0o755);
+            repaired.push(helper);
+        } catch (err) {
+            failed.push({ path: helper, error: err instanceof Error ? err.message : String(err) });
+        }
+    }
+
+    return { repaired, failed };
+}
+
+/**
+ * Proves node-pty works by actually opening a PTY, which is the only check that
+ * exercises the spawn-helper path that breaks. A `require` alone would pass on a
+ * broken install, because the helper is only touched at spawn time.
+ *
+ * @param {string} ptyDir Absolute path to the node-pty package root.
+ * @returns {{ ok: boolean, error?: string, nativeFailure?: boolean }}
+ */
+export function verifyPtySpawn(ptyDir) {
+    let child;
+    try {
+        const pty = require(ptyDir); // directory require → node-pty's "main" (lib/index.js)
+        const file = process.platform === 'win32' ? process.env.COMSPEC || 'cmd.exe' : '/bin/echo';
+        const args = process.platform === 'win32' ? ['/c', 'exit'] : ['codeman-node-pty-check'];
+        child = pty.spawn(file, args, {
+            name: 'xterm-color',
+            cols: 80,
+            rows: 24,
+            cwd: tmpdir(),
+            env: process.env,
+        });
+        return { ok: true };
+    } catch (err) {
+        const message = err instanceof Error ? err.message : String(err);
+        return { ok: false, error: message, nativeFailure: NATIVE_FAILURE_PATTERN.test(message) };
+    } finally {
+        try {
+            child?.kill();
+        } catch {
+            /* the probe child exits on its own anyway */
+        }
+    }
+}
+
+/**
+ * Rebuilds node-pty from source, preserving the prebuilds tree across a failure.
+ *
+ * node-pty's install script deletes `prebuilds/` as soon as
+ * `npm_config_build_from_source` is set and only then shells out to node-gyp, so
+ * a machine without a compiler toolchain would otherwise be left with neither a
+ * prebuilt nor a compiled binary.
+ *
+ * @param {string} ptyDir Absolute path to the node-pty package root.
+ * @param {string} cwd Directory to run npm from (the package root that owns node_modules).
+ * @returns {{ ok: boolean, error?: string }}
+ */
+function rebuildFromSource(ptyDir, cwd) {
+    const prebuilds = join(ptyDir, 'prebuilds');
+    const backup = join(ptyDir, '.prebuilds-codeman-backup');
+
+    let backedUp = false;
+    if (existsSync(prebuilds)) {
+        try {
+            rmSync(backup, { recursive: true, force: true });
+            cpSync(prebuilds, backup, { recursive: true });
+            backedUp = true;
+        } catch {
+            /* best effort: proceed without a safety net rather than skip the repair */
+        }
+    }
+
+    try {
+        execSync('npm rebuild node-pty --build-from-source', { cwd, stdio: 'pipe', timeout: 300000 });
+        return { ok: true };
+    } catch (err) {
+        if (backedUp && !existsSync(prebuilds)) {
+            try {
+                cpSync(backup, prebuilds, { recursive: true });
+            } catch {
+                /* nothing further we can do */
+            }
+        }
+        return { ok: false, error: err instanceof Error ? err.message : String(err) };
+    } finally {
+        rmSync(backup, { recursive: true, force: true });
+    }
+}
+
+/**
+ * Full repair flow: chmod, verify, and only rebuild if a working PTY still can't
+ * be opened.
+ *
+ * @param {object} [options]
+ * @param {(line: string) => void} [options.log] Progress sink (default: silent).
+ * @param {(line: string) => void} [options.warn] Warning sink (default: same as log).
+ * @param {boolean} [options.allowRebuild] Permit a from-source rebuild (default: true).
+ * @returns {Promise<{ ok: boolean, repaired: string[], rebuilt: boolean, reason?: string }>}
+ */
+export async function fixNodePty(options = {}) {
+    const log = options.log ?? (() => {});
+    const warn = options.warn ?? log;
+    const allowRebuild = options.allowRebuild ?? true;
+
+    const ptyDir = findNodePtyDir();
+    if (!ptyDir) {
+        return { ok: false, repaired: [], rebuilt: false, reason: 'node-pty is not installed' };
+    }
+
+    const { repaired, failed } = repairSpawnHelpers(ptyDir);
+    for (const f of failed) warn(`could not chmod ${f.path}: ${f.error}`);
+    if (repaired.length > 0) {
+        log(`made node-pty spawn-helper executable (${repaired.length} file${repaired.length === 1 ? '' : 's'})`);
+    }
+
+    const first = verifyPtySpawn(ptyDir);
+    if (first.ok) return { ok: true, repaired, rebuilt: false };
+
+    if (!allowRebuild || !first.nativeFailure) {
+        return { ok: false, repaired, rebuilt: false, reason: first.error };
+    }
+
+    warn(`node-pty could not open a PTY (${first.error}), rebuilding from source...`);
+    const projectRoot = join(dirname(fileURLToPath(import.meta.url)), '..');
+    const rebuild = rebuildFromSource(ptyDir, projectRoot);
+    if (!rebuild.ok) {
+        return { ok: false, repaired, rebuilt: false, reason: `rebuild failed: ${rebuild.error}` };
+    }
+
+    const after = repairSpawnHelpers(ptyDir);
+    repaired.push(...after.repaired);
+
+    const second = verifyPtySpawn(ptyDir);
+    return second.ok
+        ? { ok: true, repaired, rebuilt: true }
+        : { ok: false, repaired, rebuilt: true, reason: second.error };
+}
+
+// ---------------------------------------------------------------------------
+// CLI: node scripts/fix-node-pty.mjs [--quiet]
+// ---------------------------------------------------------------------------
+
+const isDirectRun = process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1];
+
+if (isDirectRun) {
+    const quiet = process.argv.includes('--quiet');
+    const say = (line) => {
+        if (!quiet) console.log(line);
+    };
+
+    const result = await fixNodePty({ log: say, warn: (line) => console.warn(line) });
+
+    if (result.ok) {
+        say(result.repaired.length > 0 || result.rebuilt ? 'node-pty repaired, PTY spawning works' : 'node-pty is healthy');
+        process.exit(0);
+    }
+
+    console.error(`node-pty is not usable: ${result.reason}`);
+    console.error('Try:  cd node_modules/node-pty && npx node-gyp rebuild');
+    process.exit(1);
+}

scripts/postinstall.js

@@ -6,7 +6,7 @@
  */
 
 import { execSync, spawn } from 'child_process';
-import { chmodSync, existsSync } from 'fs';
+import { existsSync } from 'fs';
 import { homedir, platform } from 'os';
 import { join } from 'path';
 import { createRequire } from 'module';
@@ -148,35 +148,32 @@ if (majorVersion < MIN_NODE_VERSION) {
 }
 
 // ----------------------------------------------------------------------------
-// 1b. Fix node-pty spawn-helper permissions (macOS posix_spawnp fix)
+// 1b. Repair + verify node-pty (macOS posix_spawnp fix, issues #6 and #204)
+//
+// node-pty ships its macOS spawn-helper without the execute bit, which breaks
+// every session start on macOS. fixNodePty() chmods it, then proves a PTY can
+// actually be opened, and only falls back to a from-source rebuild if that
+// still fails. See scripts/fix-node-pty.mjs for the full story.
 // ----------------------------------------------------------------------------
 
 try {
-    const require = createRequire(import.meta.url);
-    const ptyPath = join(require.resolve('node-pty'), '..');
-    const spawnHelper = join(ptyPath, 'build', 'Release', 'spawn-helper');
-    if (existsSync(spawnHelper)) {
-        chmodSync(spawnHelper, 0o755);
-        console.log(colors.green('✓ node-pty spawn-helper permissions fixed'));
-    }
-} catch {
-    // Non-critical — only affects macOS with prebuilt binaries
-}
+    const { fixNodePty } = await import('./fix-node-pty.mjs');
+    const result = await fixNodePty({
+        log: (line) => console.log(colors.dim(`  ${line}`)),
+        warn: (line) => console.log(colors.yellow(`⚠ ${line}`)),
+    });
 
-// ----------------------------------------------------------------------------
-// 1c. Rebuild node-pty from source for Node.js 22+ compatibility
-// ----------------------------------------------------------------------------
-
-if (majorVersion >= 22) {
-    try {
-        console.log(colors.dim('  Rebuilding node-pty from source for Node.js 22+...'));
-        execSync('npm rebuild node-pty --build-from-source', { stdio: 'pipe', timeout: 120000 });
-        console.log(colors.green('✓ node-pty rebuilt from source'));
-    } catch {
+    if (result.ok) {
+        console.log(colors.green('✓ node-pty verified') + colors.dim(' (PTY spawn works)'));
+    } else {
         hasWarnings = true;
-        console.log(colors.yellow('⚠ Failed to rebuild node-pty from source'));
-        console.log(colors.dim('  You may need to run: npm rebuild node-pty --build-from-source'));
+        console.log(colors.yellow(`⚠ node-pty is not usable: ${result.reason}`));
+        console.log(colors.dim('  Sessions will fail to start. Try: ') + colors.cyan('npm run fix:node-pty'));
     }
+} catch (err) {
+    hasWarnings = true;
+    console.log(colors.yellow(`⚠ Could not verify node-pty: ${err.message}`));
+    console.log(colors.dim('  If sessions fail to start, run: ') + colors.cyan('npm run fix:node-pty'));
 }
 
 // ----------------------------------------------------------------------------

src/cli.ts

@@ -584,7 +584,11 @@ program
     '--allow-unauthenticated-network',
     'Allow non-loopback web access without CODEMAN_PASSWORD (dangerous; terminal control is exposed)'
   )
+  .option('--multiuser', 'Enable opt-in multi-user mode (named users in ~/.codeman/users.json; env: CODEMAN_MULTIUSER)')
   .action(async (options) => {
+    // The flag is surfaced to the rest of the process via the env var so
+    // isMultiUserMode() has a single source of truth (see config/multiuser.ts).
+    if (options.multiuser) process.env.CODEMAN_MULTIUSER = '1';
     const { startWebServer } = await import('./web/server.js');
     const host = options.host;
     const port = parseInt(options.port, 10);
@@ -626,6 +630,168 @@ program
     }
   });
 
+// ============ Multi-user Commands ============
+//
+// Operate directly on ~/.codeman/users.json (via user-store) with NO running
+// server, honoring CODEMAN_INSTANCE. This is the headless bootstrap path and the
+// recovery answer to "locked out: last admin forgot password".
+
+/** Read a password from stdin without echoing. Falls back to plain read on non-TTY. */
+function promptHiddenPassword(question: string): Promise<string> {
+  const stdin = process.stdin;
+  if (!stdin.isTTY || typeof stdin.setRawMode !== 'function') {
+    // Non-interactive: read a single line from stdin.
+    return new Promise((resolve) => {
+      let buf = '';
+      stdin.setEncoding('utf8');
+      stdin.on('data', (d) => (buf += d));
+      stdin.on('end', () => resolve(buf.replace(/\r?\n$/, '')));
+    });
+  }
+  return new Promise((resolve) => {
+    process.stdout.write(question);
+    let input = '';
+    stdin.setRawMode(true);
+    stdin.resume();
+    stdin.setEncoding('utf8');
+    const onData = (chunk: string) => {
+      for (const c of chunk) {
+        if (c === '\n' || c === '\r' || c === '\u0004') {
+          stdin.setRawMode!(false);
+          stdin.pause();
+          stdin.removeListener('data', onData);
+          process.stdout.write('\n');
+          resolve(input);
+          return;
+        } else if (c === '\u0003') {
+          process.stdout.write('\n');
+          process.exit(1);
+        } else if (c === '\u007f' || c === '\b') {
+          input = input.slice(0, -1);
+        } else {
+          input += c;
+        }
+      }
+    };
+    stdin.on('data', onData);
+  });
+}
+
+function readAllStdin(): Promise<string> {
+  return new Promise((resolve) => {
+    let buf = '';
+    process.stdin.setEncoding('utf8');
+    process.stdin.on('data', (d) => (buf += d));
+    process.stdin.on('end', () => resolve(buf.replace(/\r?\n$/, '')));
+  });
+}
+
+const usersCmd = program.command('users').description('Manage multi-user accounts (~/.codeman/users.json)');
+
+usersCmd
+  .command('add <name>')
+  .description('Create a user (prompts for password; use --password-stdin for scripts)')
+  .option('--admin', 'Create as an admin')
+  .option('--password-stdin', 'Read the password from stdin instead of prompting')
+  .action(async (name, options) => {
+    const { createUser, isValidUsername } = await import('./user-store.js');
+    if (!isValidUsername(name)) {
+      console.error(chalk.red('✗ Username must be lowercase, start alphanumeric, 2-32 chars ([a-z0-9_-])'));
+      process.exit(1);
+    }
+    try {
+      let password: string;
+      if (options.passwordStdin) {
+        password = await readAllStdin();
+      } else {
+        password = await promptHiddenPassword('New password: ');
+        const confirm = await promptHiddenPassword('Confirm password: ');
+        if (password !== confirm) {
+          console.error(chalk.red('✗ Passwords do not match'));
+          process.exit(1);
+        }
+      }
+      if (!password || password.length < 8) {
+        console.error(chalk.red('✗ Password must be at least 8 characters'));
+        process.exit(1);
+      }
+      const user = await createUser({ username: name, role: options.admin ? 'admin' : 'user', password });
+      console.log(chalk.green(`✓ Created ${user.role} "${user.username}"`));
+    } catch (err) {
+      console.error(chalk.red(`✗ ${getErrorMessage(err)}`));
+      process.exit(1);
+    }
+  });
+
+usersCmd
+  .command('passwd <name>')
+  .description('Reset a user password')
+  .option('--password-stdin', 'Read the new password from stdin instead of prompting')
+  .action(async (name, options) => {
+    const { setPassword } = await import('./user-store.js');
+    try {
+      let password: string;
+      if (options.passwordStdin) {
+        password = await readAllStdin();
+      } else {
+        password = await promptHiddenPassword('New password: ');
+        const confirm = await promptHiddenPassword('Confirm password: ');
+        if (password !== confirm) {
+          console.error(chalk.red('✗ Passwords do not match'));
+          process.exit(1);
+        }
+      }
+      await setPassword(name, password, { mustChangePassword: false });
+      console.log(chalk.green(`✓ Password updated for "${name}"`));
+    } catch (err) {
+      console.error(chalk.red(`✗ ${getErrorMessage(err)}`));
+      process.exit(1);
+    }
+  });
+
+usersCmd
+  .command('list')
+  .alias('ls')
+  .description('List all users')
+  .action(async () => {
+    const { readUsers } = await import('./user-store.js');
+    const users = await readUsers(true);
+    if (users.length === 0) {
+      console.log(chalk.yellow('No users defined (run: codeman users add <name> --admin)'));
+      return;
+    }
+    console.log(chalk.bold('\nUsers:'));
+    for (const u of users) {
+      const role = u.role === 'admin' ? chalk.magenta('admin') : chalk.cyan('user ');
+      const state = u.disabled ? chalk.red('disabled') : chalk.green('enabled ');
+      const flags = [u.mustChangePassword ? 'must-change-pw' : '', u.canBypassPermissions ? 'can-bypass' : '']
+        .filter(Boolean)
+        .join(' ');
+      console.log(`  ${role} ${state} ${u.username}${flags ? chalk.gray(`  [${flags}]`) : ''}`);
+    }
+    console.log('');
+  });
+
+usersCmd
+  .command('rm <name>')
+  .description('Delete a user')
+  .option('--delete-space', "Also delete the user's ~/codeman-users/<name> space")
+  .action(async (name, options) => {
+    const { deleteUser, deleteUserSpace } = await import('./user-store.js');
+    try {
+      await deleteUser(name);
+      if (options.deleteSpace) {
+        await deleteUserSpace(name);
+        console.log(chalk.green(`✓ Deleted user "${name}" and their space`));
+      } else {
+        console.log(chalk.green(`✓ Deleted user "${name}" (space left on disk)`));
+      }
+    } catch (err) {
+      console.error(chalk.red(`✗ ${getErrorMessage(err)}`));
+      process.exit(1);
+    }
+  });
+
 program
   .command('doctor')
   .alias('check-deps')

src/config/auth-config.ts

@@ -31,5 +31,10 @@ export const AUTH_FAILURE_WINDOW_MS = 15 * 60 * 1000;
 // Hooks
 // ============================================================================
 
-/** Timeout for Claude Code hook curl commands (ms) */
-export const HOOK_TIMEOUT_MS = 10000;
+/**
+ * Timeout for Claude Code hook curl commands, in SECONDS: the hook `timeout`
+ * field is seconds (the CLI multiplies by 1000). The predecessor constant
+ * `HOOK_TIMEOUT_MS = 10000` fed the same field, so those hooks effectively had a
+ * ~2.8-hour timeout; 10 seconds is the originally intended budget.
+ */
+export const HOOK_TIMEOUT_SECONDS = 10;

src/config/dependency-registry.ts

@@ -98,6 +98,14 @@ export const DEPENDENCY_REGISTRY: ToolDependency[] = [
     usedBy: ['Gemini sessions'],
     resolvers: [{ match: ALL, resolver: { kind: 'path', bins: ['gemini'], versionArg: '--version' } }],
   },
+  {
+    id: 'antigravity',
+    label: 'Antigravity CLI',
+    category: 'core',
+    required: false,
+    usedBy: ['Antigravity sessions'],
+    resolvers: [{ match: ALL, resolver: { kind: 'path', bins: ['agy'], versionArg: '--version' } }],
+  },
   {
     id: 'libreoffice',
     label: 'LibreOffice',

src/config/multiuser.ts

@@ -0,0 +1,63 @@
+/**
+ * @fileoverview Multi-user mode gating + limits (opt-in, off by default).
+ *
+ * Multi-user mode is enabled by `codeman web --multiuser` (which sets
+ * `CODEMAN_MULTIUSER=1`) or the env var directly. When OFF, behavior is
+ * byte-identical to today: `users.json` is never read and all ownership scoping
+ * is bypassed. Everything here is per-instance like the rest of Codeman: a beta
+ * instance (`CODEMAN_INSTANCE=beta`) has its own `users.json` via `dataPath()`,
+ * and its user spaces live under the same shared `~/codeman-users` as prod (like
+ * `~/codeman-cases`), unless `CODEMAN_USER_SPACES_DIR` overrides it.
+ *
+ * See `docs/multi-user-plan.md` sections 3, 4.2, and 11.
+ */
+
+import { homedir } from 'node:os';
+import { join } from 'node:path';
+import { MAX_CONCURRENT_SESSIONS } from './map-limits.js';
+
+/**
+ * Whether multi-user mode is active. Read from the environment each call so it is
+ * stable for the process lifetime (env does not change after boot) and trivially
+ * overridable in tests. Accepts `1` or `true`.
+ */
+export function isMultiUserMode(): boolean {
+  const v = process.env.CODEMAN_MULTIUSER;
+  return v === '1' || v === 'true';
+}
+
+/**
+ * Root of per-user spaces: `~/codeman-users` (sibling of `~/codeman-cases`).
+ * Overridable via `CODEMAN_USER_SPACES_DIR` (used by tests). Resolved lazily so a
+ * test can point it at a temp dir before the first call.
+ */
+export function getUserSpacesDir(): string {
+  return process.env.CODEMAN_USER_SPACES_DIR || join(homedir(), 'codeman-users');
+}
+
+/** Absolute path to a user's top-level space: `<USER_SPACES_DIR>/<username>[/segments]`. */
+export function userSpacePath(username: string, ...segments: string[]): string {
+  return join(getUserSpacesDir(), username, ...segments);
+}
+
+/** Absolute path to a user's cases dir: `<USER_SPACES_DIR>/<username>/cases`. */
+export function userCasesDir(username: string): string {
+  return join(getUserSpacesDir(), username, 'cases');
+}
+
+/** Maximum number of user accounts (default 25, env `CODEMAN_MAX_USERS`). */
+export function maxUsers(): number {
+  const n = Number(process.env.CODEMAN_MAX_USERS);
+  return Number.isInteger(n) && n > 0 ? n : 25;
+}
+
+/**
+ * Per-user concurrent-session cap (the fairness lever). Defaults to half the
+ * global cap; overridable via `CODEMAN_MAX_SESSIONS_PER_USER`. The global cap
+ * (MAX_CONCURRENT_SESSIONS) still applies on top and is shared across users.
+ */
+export function maxSessionsPerUser(): number {
+  const n = Number(process.env.CODEMAN_MAX_SESSIONS_PER_USER);
+  if (Number.isInteger(n) && n > 0) return n;
+  return Math.max(1, Math.floor(MAX_CONCURRENT_SESSIONS / 2));
+}

src/config/webview-limits.ts

@@ -0,0 +1,49 @@
+/**
+ * Limits and timeouts for web tabs (dashboards embedded as Codeman tabs).
+ *
+ * Every value here bounds something an untrusted-ish upstream controls: how many
+ * dashboards can be saved, how long the server will wait on one, how much of a
+ * response it will buffer before rewriting HTML, and how many sockets a single
+ * dashboard may hold open. Env-overridable in the same style as the other config
+ * modules.
+ */
+
+function envInt(name: string, fallback: number): number {
+  const parsed = parseInt(process.env[name] || '', 10);
+  return Number.isFinite(parsed) && parsed > 0 ? parsed : fallback;
+}
+
+/** Max saved webviews (per owner in multi-user mode). */
+export const MAX_WEBVIEWS = envInt('CODEMAN_MAX_WEBVIEWS', 50);
+
+/**
+ * Max iframes kept mounted at once. Switching tabs must not reload a dashboard,
+ * so frames stay alive while hidden; past this many, the least-recently-viewed
+ * frame is evicted. Consumed by the frontend via `GET /api/webviews`.
+ */
+export const MAX_LIVE_WEBVIEW_FRAMES = envInt('CODEMAN_MAX_LIVE_WEBVIEW_FRAMES', 6);
+
+/** How long a minted proxy capability stays valid (rolling, refreshed on use). */
+export const WEBVIEW_CAPABILITY_TTL_MS = envInt('CODEMAN_WEBVIEW_CAPABILITY_TTL_MS', 12 * 60 * 60 * 1000);
+
+/** Max concurrent capabilities held in memory before the oldest are dropped. */
+export const MAX_WEBVIEW_CAPABILITIES = 200;
+
+/** Upstream request timeout for a proxied HTTP request. */
+export const WEBVIEW_UPSTREAM_TIMEOUT_MS = envInt('CODEMAN_WEBVIEW_TIMEOUT_MS', 30_000);
+
+/** Shorter timeout for the editor's "Test" probe, which a human is waiting on. */
+export const WEBVIEW_PROBE_TIMEOUT_MS = envInt('CODEMAN_WEBVIEW_PROBE_TIMEOUT_MS', 8_000);
+
+/**
+ * Max bytes of an HTML response buffered for `<base>` injection and link
+ * rewriting. Larger HTML documents stream through untouched: the rewrite is a
+ * convenience, and buffering an unbounded upstream body is a memory hazard.
+ */
+export const MAX_WEBVIEW_HTML_REWRITE_BYTES = envInt('CODEMAN_MAX_WEBVIEW_HTML_BYTES', 8 * 1024 * 1024);
+
+/** Max concurrent proxied WebSockets per webview (mirrors MAX_WS_PER_SESSION). */
+export const MAX_WEBVIEW_SOCKETS = envInt('CODEMAN_MAX_WEBVIEW_SOCKETS', 8);
+
+/** URL path prefix the proxy is mounted at. Single source of truth. */
+export const WEBVIEW_PROXY_PREFIX = '/webview';

src/cron/cron-service.ts

@@ -15,6 +15,8 @@ import { SseEvent } from '../web/sse-events.js';
 import { CronJobSchema } from '../web/schemas.js';
 import { getErrorMessage, createErrorResponse, ApiErrorCode } from '../types/api.js';
 import { MAX_CONCURRENT_SESSIONS, MAX_CRON_JOBS, MAX_CRON_RUN_HISTORY } from '../config/map-limits.js';
+import { canUsernameRunPrivilegedCommands, resolveClaudeModeForUsername } from '../user-store.js';
+import { sessionCapacityState, isWorkingDirAllowedForUsername } from '../web/route-helpers.js';
 import { CRON_READY_MAX_ATTEMPTS, CRON_READY_SETTLE_MS } from '../config/server-timing.js';
 import {
   DEFAULT_BLOCKED_TREES,
@@ -25,6 +27,7 @@ import { validateSessionFilePath } from '../web/route-helpers.js';
 import { computeNextRunAt, dueKeyFor } from './cron-time.js';
 import type { SessionPort, EventPort, ConfigPort, InfraPort } from '../web/ports/index.js';
 import type { CronJob, CronJobRun, CronJobRunStatus, TriggerType } from '../types/cron.js';
+import type { GeminiConfig } from '../types/session.js';
 import type { CronJobInput } from './cron-input.js';
 
 /** The subset of the route context the cron depends on. */
@@ -108,7 +111,7 @@ export class CronService {
 
   // ──────────────────────────── Mutations ───────────────────────────
 
-  createJob(input: CronJobInput): CronJob {
+  createJob(input: CronJobInput, owner?: string): CronJob {
     if (Object.keys(this.store.getCronJobs()).length >= MAX_CRON_JOBS) {
       throw this.badRequest(`Maximum number of cron jobs (${MAX_CRON_JOBS}) reached`);
     }
@@ -117,6 +120,7 @@ export class CronService {
     const job: CronJob = {
       id: uuidv4(),
       name: input.name,
+      owner,
       agentType: input.agentType,
       workingDir: input.workingDir,
       launchCommand: input.launchCommand,
@@ -328,6 +332,12 @@ export class CronService {
       return this.failRun(job, run, 'workingDir does not exist');
     }
 
+    // Section 6.3: defense-in-depth workingDir confinement re-check at FIRE time against the
+    // owner's CURRENT space (complements the create/update gate). No-op in single-user / unset owner.
+    if (!(await isWorkingDirAllowedForUsername(job.owner, job.workingDir))) {
+      return this.failRun(job, run, 'workingDir is outside the owner workspace');
+    }
+
     // Recurring jobs: close the still-open session created by this job's
     // previous run before launching the next (default ON, opt-out via
     // autoClosePreviousSession:false) — otherwise an unattended interval/daily
@@ -336,10 +346,21 @@ export class CronService {
       await this.closePreviousRunSessions(job, run.id);
     }
 
-    // Respect the global session cap.
-    if (this.deps.sessions.size >= MAX_CONCURRENT_SESSIONS) {
+    // Respect the global cap AND the owner's per-user cap (multi-user).
+    const cap = sessionCapacityState(this.deps.sessions, job.owner);
+    if (cap.atGlobalCap) {
       return this.failRun(job, run, `Maximum concurrent sessions (${MAX_CONCURRENT_SESSIONS}) reached`);
     }
+    if (cap.atUserCap) {
+      return this.failRun(job, run, `Owner's per-user session limit reached`);
+    }
+
+    // Section 6.3: re-resolve the owner's grant at FIRE time (it may have been revoked
+    // since create). Gates shell/launchCommand AND clamps the external-CLI bypass below.
+    const ownerGranted = await canUsernameRunPrivilegedCommands(job.owner);
+    if ((job.agentType === 'shell' || job.launchCommand) && !ownerGranted) {
+      return this.failRun(job, run, 'Owner lacks the can-bypass-permissions grant for shell/launchCommand jobs');
+    }
 
     // Create + start the session (mirrors the quick-start route flow).
     let session: Session;
@@ -348,7 +369,15 @@ export class CronService {
       const globalNice = await this.deps.getGlobalNiceConfig();
       const modelConfig = await this.deps.getModelConfig();
       const claudeModeConfig = await this.deps.getClaudeModeConfig();
+      const effectiveClaudeMode = await resolveClaudeModeForUsername(claudeModeConfig.claudeMode, job.owner);
       const model = mode !== 'shell' ? modelConfig?.defaultModel || undefined : undefined;
+      // Section 6.3: cron carries no per-CLI config, so buildGeminiCommand(undefined)
+      // would default a non-granted owner to `--approval-mode yolo` (classifier-free) —
+      // materialize auto_edit for a non-granted gemini owner, mirroring the route clamp
+      // (#15). Granted/admin/single-user leave it undefined → yolo parity. Codex's absent
+      // config already defaults to the safe sandbox, so no clamp is needed there.
+      const geminiConfig: GeminiConfig | undefined =
+        mode === 'gemini' && !ownerGranted ? { approvalMode: 'auto_edit' } : undefined;
       session = new Session({
         workingDir: job.workingDir,
         mode,
@@ -357,8 +386,10 @@ export class CronService {
         useMux: true,
         niceConfig: globalNice,
         model,
-        claudeMode: claudeModeConfig.claudeMode,
+        claudeMode: effectiveClaudeMode,
         allowedTools: claudeModeConfig.allowedTools,
+        geminiConfig,
+        owner: job.owner,
       });
       this.deps.addSession(session);
       this.store.incrementSessionsCreated();

src/docker-export.ts

@@ -105,6 +105,45 @@ export function parseLoadedImageRef(loadOutput: string): string | null {
   return null;
 }
 
+/**
+ * Validate an imported bundle's manifest BEFORE any of its fields are trusted.
+ * A bundle is cross-machine input (potentially authored by someone else), and its
+ * fields flow into stored host/case config that the schema layer never sees:
+ * `engine` becomes the probe/launch binary selector, `image`/`containerWorkdir`
+ * reach the shellescaped launch string, `network` is a create arg. Mirror the
+ * DockerHostSchema/DockerCaseLinkSchema constraints here (throwing, since this is
+ * not a web-layer module). Exported for unit tests.
+ */
+export function validateImportManifest(manifest: DockerExportManifest): void {
+  const fail = (msg: string): never => {
+    throw new Error(`invalid bundle manifest: ${msg}`);
+  };
+  if (manifest.schemaVersion !== DOCKER_EXPORT_SCHEMA) {
+    fail(`unsupported export schema version ${manifest.schemaVersion} (expected ${DOCKER_EXPORT_SCHEMA})`);
+  }
+  if (manifest.mode !== 'full' && manifest.mode !== 'workspace') fail(`unknown mode ${String(manifest.mode)}`);
+  if (manifest.engine !== 'docker' && manifest.engine !== 'podman') fail(`unknown engine ${String(manifest.engine)}`);
+  if (typeof manifest.caseName !== 'string' || !/^[a-zA-Z0-9_-]+$/.test(manifest.caseName)) fail('bad caseName');
+  if (
+    typeof manifest.image !== 'string' ||
+    manifest.image.length > 512 ||
+    !/^[a-zA-Z0-9][\w./:@-]*$/.test(manifest.image)
+  ) {
+    fail('bad image reference');
+  }
+  if (
+    typeof manifest.containerWorkdir !== 'string' ||
+    manifest.containerWorkdir.length > 2000 ||
+    !manifest.containerWorkdir.startsWith('/') ||
+    // comma: --mount specs are comma-delimited CSV; shell escaping cannot protect it
+    /[`$\\"'\n\r;&|<>,]/.test(manifest.containerWorkdir)
+  ) {
+    fail('bad containerWorkdir');
+  }
+  if (!['bridge', 'none', 'custom'].includes(manifest.network)) fail(`unknown network ${String(manifest.network)}`);
+  if (typeof manifest.checksums !== 'object' || manifest.checksums === null) fail('missing checksums');
+}
+
 // ========== IO helpers ==========
 
 function run(
@@ -338,25 +377,34 @@ export async function importDockerBundle(params: {
   destWorkspace: string;
   engine: DockerEngine;
   timestamp: number;
+  /** Schema-validated destination case name; the quarantine tag derives from THIS,
+   *  never from the (attacker-authored) manifest.caseName. */
+  newCaseName: string;
 }): Promise<ImportResult> {
-  const { bundlePath, destWorkspace, engine, timestamp } = params;
+  const { bundlePath, destWorkspace, engine, timestamp, newCaseName } = params;
   const argv: string[] = [engine === 'podman' ? 'podman' : 'docker'];
 
   if (IS_TEST_MODE) {
     const raw = await fs.readFile(bundlePath, 'utf-8').catch(() => '{}');
-    return { manifest: JSON.parse(raw) as DockerExportManifest, workspacePath: destWorkspace };
+    const manifest = JSON.parse(raw) as DockerExportManifest;
+    validateImportManifest(manifest);
+    return { manifest, workspacePath: destWorkspace };
   }
 
   const stageDir = `${destWorkspace}.import-stage-${timestamp}`;
   mkdirSync(stageDir, { recursive: true });
   try {
-    await run('tar', ['-xzf', bundlePath, '-C', stageDir], { timeout: 300_000 });
+    // Outer-bundle traversal guard (defense in depth: GNU/bsd tar already refuse
+    // `..`/absolute members by default, but the bundle is cross-machine input).
+    const { stdout: bundleMembers } = await run('tar', ['-tzf', bundlePath], { timeout: 60_000 });
+    for (const member of bundleMembers.split('\n').filter(Boolean)) {
+      if (!isSafeTarMember(member)) throw new Error(`unsafe path in bundle archive: ${member}`);
+    }
+    await run('tar', ['--no-same-owner', '-xzf', bundlePath, '-C', stageDir], { timeout: 300_000 });
 
     const manifestRaw = await fs.readFile(join(stageDir, 'manifest.json'), 'utf-8');
     const manifest = JSON.parse(manifestRaw) as DockerExportManifest;
-    if (manifest.schemaVersion !== DOCKER_EXPORT_SCHEMA) {
-      throw new Error(`unsupported export schema version ${manifest.schemaVersion} (expected ${DOCKER_EXPORT_SCHEMA})`);
-    }
+    validateImportManifest(manifest);
 
     // Integrity: verify checksums before trusting any member.
     const workspaceTar = join(stageDir, 'workspace.tar');
@@ -385,8 +433,9 @@ export async function importDockerBundle(params: {
       const { stdout } = await run(argv[0], [...argv.slice(1), 'load', '-i', imageTar], { timeout: 300_000 });
       const loadedRef = parseLoadedImageRef(stdout);
       if (!loadedRef) throw new Error('could not determine loaded image ref');
-      // Quarantine: re-tag by the loaded ref/id, never trusting the bundle's original tag.
-      importedImage = importedImageTag(manifest.caseName, timestamp);
+      // Quarantine: re-tag by the loaded ref/id, never trusting the bundle's original
+      // tag; the tag name derives from the caller's schema-validated newCaseName.
+      importedImage = importedImageTag(newCaseName, timestamp);
       await run(argv[0], [...argv.slice(1), 'tag', loadedRef, importedImage], { timeout: 60_000 });
     }
 

src/docker-hosts.ts

@@ -21,13 +21,15 @@
  * @module docker-hosts
  */
 
-import { existsSync, mkdirSync } from 'node:fs';
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs';
 import fs from 'node:fs/promises';
-import { join } from 'node:path';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
 import { homedir } from 'node:os';
 import { createHash } from 'node:crypto';
-import { execFile } from 'node:child_process';
+import { execFile, spawn } from 'node:child_process';
 import { promisify } from 'node:util';
+import { dataPath } from './config/instance.js';
 import type {
   DockerCase,
   DockerCommandMode,
@@ -107,6 +109,24 @@ export async function writeDockerCases(configDir: string, cases: DockerCase[]):
   await writeJsonArray(configDir, dockerCasesPath(configDir), cases);
 }
 
+/**
+ * Persist the case's last Claude conversation id (the `--resume` seed for the
+ * container-recreated relaunch, docs/docker-cases-plan.md two-layer durability).
+ * Keyed by container name so callers that only hold a SessionDocker can update it.
+ * No-op when the id is unchanged or the case is gone.
+ */
+export async function persistDockerCaseClaudeSessionId(
+  configDir: string,
+  containerName: string,
+  claudeSessionId: string
+): Promise<void> {
+  const cases = await readDockerCases(configDir);
+  const idx = cases.findIndex((c) => (c.container ?? dockerContainerName(c.name)) === containerName);
+  if (idx === -1 || cases[idx].lastClaudeSessionId === claudeSessionId) return;
+  cases[idx] = { ...cases[idx], lastClaudeSessionId: claudeSessionId };
+  await writeDockerCases(configDir, cases);
+}
+
 // ========== Naming / display / defaults ==========
 
 /** Per-case container name. Mirrors how remote derives a stable name from the case. */
@@ -123,6 +143,7 @@ export function defaultDockerCommandForMode(mode: SessionMode): string {
     opencode: 'exec opencode',
     codex: 'exec codex',
     gemini: 'exec gemini',
+    antigravity: 'exec agy',
   };
   return commands[mode as DockerCommandMode] || commands.shell;
 }
@@ -388,37 +409,307 @@ export function buildDockerCreateArgs(ctx: DockerCreateContext): string[] {
   return args;
 }
 
+/**
+ * PURE argv for building the agent base image locally (the programmatic mirror of
+ * scripts/build-agent-image.mjs): `build -f <dockerfile> -t <image> [--no-cache]
+ * <contextDir>`. Kept pure + unit-testable; the caller prepends the engine binary.
+ */
+export function agentImageBuildArgs(dockerfile: string, image: string, contextDir: string, noCache = false): string[] {
+  return ['build', '-f', dockerfile, '-t', image, ...(noCache ? ['--no-cache'] : []), contextDir];
+}
+
 // ========== Credential mount resolution (IO) ==========
 
-/** Host cred paths mapped to their in-container HOME location. */
-const CREDENTIAL_PATHS: Array<{ rel: string }> = [
-  { rel: '.claude' },
-  { rel: '.claude.json' },
-  { rel: '.codex' },
-  { rel: '.gemini' },
-  { rel: '.config/gcloud' },
-  { rel: '.config/opencode' },
+/** Container Claude config dir (created gid-0 writable in the image). */
+export const CONTAINER_CLAUDE_DIR = `${CONTAINER_HOME}/.claude`;
+/** In-container path of the seeded (writable) `~/.claude.json`. */
+export const CLAUDE_JSON_HOME = `${CONTAINER_HOME}/.claude.json`;
+/** In-container path of the read-only host-seeded `~/.claude.json` (copied into HOME at launch). */
+export const CLAUDE_JSON_SEED = `${CONTAINER_HOME}/.codeman/claude.seed.json`;
+/** Read-only seed paths for the files copied into the container's `.claude`. */
+const CLAUDE_CREDS_SEED = `${CONTAINER_HOME}/.codeman/claude-creds.seed.json`;
+const CLAUDE_SETTINGS_SEED = `${CONTAINER_HOME}/.codeman/claude-settings.seed.json`;
+const CLAUDE_STATS_SEED = `${CONTAINER_HOME}/.codeman/claude-stats.seed.json`;
+/** Staging root for read-only host-cred seed mounts (codex/gemini/gcloud/opencode). */
+const CRED_SEED_DIR = `${CONTAINER_HOME}/.codeman/cred-seeds`;
+
+/**
+ * PURE: merge the host `~/.claude.json` into a config that makes an
+ * already-authenticated Claude skip its INTERACTIVE onboarding inside the container
+ * (the host file itself lacks these flags — the host install is grandfathered, so a
+ * verbatim copy still triggers the theme picker + login wizard + folder-trust
+ * prompt). Forces `hasCompletedOnboarding`, a `theme` (so the theme picker is
+ * skipped), and marks the workspace project trusted + onboarded. Auth still comes
+ * from the copied `oauthAccount` + the dir-mounted `~/.claude/.credentials.json`.
+ */
+export function buildSeamlessClaudeConfig(
+  hostConfig: Record<string, unknown>,
+  workspacePath: string,
+  theme = 'dark'
+): Record<string, unknown> {
+  const merged: Record<string, unknown> = { ...hostConfig };
+  merged.hasCompletedOnboarding = true;
+  if (typeof merged.theme !== 'string') merged.theme = theme;
+  const projects = { ...((merged.projects as Record<string, Record<string, unknown>> | undefined) ?? {}) };
+  const existing = (projects[workspacePath] as Record<string, unknown> | undefined) ?? {};
+  const seenCount = existing.projectOnboardingSeenCount;
+  projects[workspacePath] = {
+    ...existing,
+    hasTrustDialogAccepted: true,
+    hasCompletedProjectOnboarding: true,
+    projectOnboardingSeenCount: typeof seenCount === 'number' && seenCount > 0 ? seenCount : 1,
+  };
+  merged.projects = projects;
+  return merged;
+}
+
+/** Best-effort read of the host `~/.claude/settings.json` theme (drives the seed's theme). */
+function readHostClaudeTheme(home: string): string | undefined {
+  try {
+    const parsed = JSON.parse(readFileSync(join(home, '.claude', 'settings.json'), 'utf-8')) as { theme?: unknown };
+    return typeof parsed.theme === 'string' ? parsed.theme : undefined;
+  } catch {
+    return undefined;
+  }
+}
+
+/**
+ * Resolve the read-only seed mount for `~/.claude.json`. Reads the host file, merges
+ * in the seamless-onboarding flags + workspace trust (buildSeamlessClaudeConfig),
+ * writes the result to a per-container seed file under `~/.codeman/docker-seeds/`,
+ * and returns its mount. The launch chain copies it to `~/.claude.json` inside HOME
+ * once — giving Claude a NORMAL writable, already-onboarded config (no atomic-rename
+ * EBUSY, no re-auth, no theme/trust prompts). Falls back to the RAW host file when
+ * parse/write fails (auth still works; the wizard may show). Returns null when the
+ * host has no `~/.claude.json`. IO; under VITEST returns the raw mount (no write).
+ */
+export function resolveClaudeJsonSeedMount(
+  home: string = homedir(),
+  containerName?: string,
+  workspacePath?: string
+): DockerMount | null {
+  const src = join(home, '.claude.json');
+  if (!existsSync(src)) return null;
+  const rawMount: DockerMount = { src, dst: CLAUDE_JSON_SEED, readonly: true };
+  if (IS_TEST_MODE || !containerName || !workspacePath) return rawMount;
+  try {
+    const hostConfig = JSON.parse(readFileSync(src, 'utf-8')) as Record<string, unknown>;
+    const merged = buildSeamlessClaudeConfig(hostConfig, workspacePath, readHostClaudeTheme(home) ?? 'dark');
+    const seedsDir = dataPath('docker-seeds');
+    if (!existsSync(seedsDir)) mkdirSync(seedsDir, { recursive: true });
+    const seedFile = join(seedsDir, `${containerName}.json`);
+    writeFileSync(seedFile, JSON.stringify(merged), { mode: 0o600 });
+    return { src: seedFile, dst: CLAUDE_JSON_SEED, readonly: true };
+  } catch {
+    return rawMount; // partial host write / unreadable — auth still carries, wizard may show
+  }
+}
+
+/** A file (or dir, when `recursive`) copied into the container HOME once at launch
+ *  (`[ -e to ] || cp [-a] from to`). */
+export interface DockerSeedCopy {
+  from: string;
+  to: string;
+  /** `cp -a` for whole-directory credential seeds (gemini/gcloud/opencode). */
+  recursive?: boolean;
+}
+
+export interface DockerClaudeArtifacts {
+  /** Bind mounts to add: the shared `projects/` transcripts (RW) + read-only seed files. */
+  mounts: DockerMount[];
+  /** Files copied into the container's writable HOME/.claude (+ HOME/.claude.json) at launch. */
+  seedCopies: DockerSeedCopy[];
+}
+
+/**
+ * Resolve the ISOLATED Claude artifacts for a docker session (replaces the old
+ * whole-`~/.claude` RW mount that polluted the host). Shares ONLY what must cross
+ * the boundary and seeds the rest as writable copies:
+ *  - `~/.claude/projects` → RW dir mount (transcripts: host watchers + `--resume`).
+ *  - `~/.claude.json` → merged onboarding seed, copied to HOME (no re-auth/wizard).
+ *  - `~/.claude/.credentials.json` + `~/.claude/settings.json` → read-only seeds
+ *    copied into the container's own `~/.claude` (token + global prefs carry in;
+ *    the container refreshes its own copy and never writes back to the host).
+ * Everything else Claude writes (backups, tasks, teams, session-env, history) stays
+ * container-local. IO (reads host files, writes the merged `.claude.json` seed).
+ */
+export function resolveDockerClaudeArtifacts(
+  home: string,
+  containerName: string,
+  workspacePath: string
+): DockerClaudeArtifacts {
+  const mounts: DockerMount[] = [];
+  const seedCopies: DockerSeedCopy[] = [];
+
+  // The ONE genuinely-shared part: conversation transcripts (dir mount → renames work).
+  const projectsSrc = join(home, '.claude', 'projects');
+  if (existsSync(projectsSrc)) {
+    mounts.push({ src: projectsSrc, dst: `${CONTAINER_CLAUDE_DIR}/projects` });
+  }
+
+  // ~/.claude.json → merged, onboarding-complete seed at HOME root.
+  const jsonSeed = resolveClaudeJsonSeedMount(home, containerName, workspacePath);
+  if (jsonSeed) {
+    mounts.push(jsonSeed);
+    seedCopies.push({ from: CLAUDE_JSON_SEED, to: CLAUDE_JSON_HOME });
+  }
+
+  // credentials (token) + settings (theme/model/effort/permissions) + stats-cache
+  // (drives the model/effort status indicator) → writable copies inside the
+  // container's own ~/.claude (never a wholesale mount → no host pollution).
+  const files: Array<[rel: string, seed: string, dest: string]> = [
+    ['.credentials.json', CLAUDE_CREDS_SEED, `${CONTAINER_CLAUDE_DIR}/.credentials.json`],
+    ['settings.json', CLAUDE_SETTINGS_SEED, `${CONTAINER_CLAUDE_DIR}/settings.json`],
+    ['stats-cache.json', CLAUDE_STATS_SEED, `${CONTAINER_CLAUDE_DIR}/stats-cache.json`],
+  ];
+  for (const [rel, seed, dest] of files) {
+    const src = join(home, '.claude', rel);
+    if (existsSync(src)) {
+      mounts.push({ src, dst: seed, readonly: true });
+      seedCopies.push({ from: seed, to: dest });
+    }
+  }
+
+  return { mounts, seedCopies };
+}
+
+/**
+ * Per-CLI credential-store isolation policy (the codex/gemini/gcloud/opencode analog
+ * of resolveDockerClaudeArtifacts). Codex is the direct Claude-analog: its
+ * `sessions/` rollouts + `history.jsonl` are read HOST-SIDE (response-viewer +
+ * `codex resume`), so they are SHARED (RW), while `auth.json`/`config.toml` are
+ * seeded. The other three have no host-read/resume dependency and are fully
+ * seed-copied (writable copy in the container, no write-back to the host).
+ */
+interface CredStorePolicy {
+  /** Path relative to HOME (host + container), e.g. '.codex' or '.config/gcloud'. */
+  rel: string;
+  /** Subdirs bind-mounted RW (shared: resume + host reads). */
+  shareDirs?: string[];
+  /** Files bind-mounted RW (append-only, e.g. codex history.jsonl — never renamed). */
+  shareFiles?: string[];
+  /** Files seeded (RO mount → cp) into the container's own copy. */
+  seedFiles?: string[];
+  /** Seed the WHOLE dir (RO mount → cp -a) — for stores with no shared/host-read state. */
+  seedWhole?: boolean;
+}
+
+const CRED_STORES: CredStorePolicy[] = [
+  { rel: '.codex', shareDirs: ['sessions'], shareFiles: ['history.jsonl'], seedFiles: ['auth.json', 'config.toml'] },
+  { rel: '.gemini', seedWhole: true },
+  { rel: '.config/gcloud', seedWhole: true },
+  { rel: '.config/opencode', seedWhole: true },
 ];
 
 /**
- * Resolve which host credential dirs/files EXIST and map them to their container
- * HOME location. Only-existing avoids docker auto-creating root-owned empty dirs
- * in the user's home. `~/.claude` also carries the transcripts (bind-mounted so
- * host watchers + `--resume` see them) and is therefore mounted read-WRITE.
+ * Resolve the ISOLATED codex/gemini/gcloud/opencode artifacts (replaces the old
+ * whole-dir RW mounts that let each in-container CLI write its refreshed tokens +
+ * session state back into the host). Every path is existsSync-gated (on most hosts
+ * only a subset exists). Pure-ish IO (no writes; just existence checks + mount specs).
  */
-export function resolveCredentialMounts(home: string = homedir()): DockerMount[] {
+export function resolveDockerCredentialArtifacts(home: string = homedir()): DockerClaudeArtifacts {
   const mounts: DockerMount[] = [];
-  for (const { rel } of CREDENTIAL_PATHS) {
-    const src = join(home, rel);
-    if (existsSync(src)) {
-      mounts.push({ src, dst: `${CONTAINER_HOME}/${rel}` });
+  const seedCopies: DockerSeedCopy[] = [];
+  for (const store of CRED_STORES) {
+    const hostBase = join(home, store.rel);
+    if (!existsSync(hostBase)) continue;
+    const containerBase = `${CONTAINER_HOME}/${store.rel}`;
+    const seedName = store.rel.replace(/\//g, '-'); // '.config/gcloud' → '.config-gcloud'
+    if (store.seedWhole) {
+      const seed = `${CRED_SEED_DIR}/${seedName}`;
+      mounts.push({ src: hostBase, dst: seed, readonly: true });
+      seedCopies.push({ from: seed, to: containerBase, recursive: true });
+      continue;
+    }
+    for (const sub of store.shareDirs ?? []) {
+      const src = join(hostBase, sub);
+      if (existsSync(src)) mounts.push({ src, dst: `${containerBase}/${sub}` });
+    }
+    for (const file of store.shareFiles ?? []) {
+      const src = join(hostBase, file);
+      if (existsSync(src)) mounts.push({ src, dst: `${containerBase}/${file}` });
+    }
+    for (const file of store.seedFiles ?? []) {
+      const src = join(hostBase, file);
+      if (existsSync(src)) {
+        const seed = `${CRED_SEED_DIR}/${seedName}-${file}`;
+        mounts.push({ src, dst: seed, readonly: true });
+        seedCopies.push({ from: seed, to: `${containerBase}/${file}` });
+      }
     }
   }
-  return mounts;
+  return { mounts, seedCopies };
 }
 
 // ========== Daemon probes (IO; no-op under VITEST) ==========
 
+/**
+ * UNESCAPED argv prefix for execFile-based probes. The shellescaped
+ * buildDockerBaseArgs variant is for interpolation into the `bash -c` launch
+ * string; argv arrays must NOT carry literal quotes (mirror of docker-export's
+ * dockerArgv).
+ */
+function dockerEngineArgv(docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost'>): string[] {
+  const argv: string[] = [docker.engine === 'podman' ? 'podman' : 'docker'];
+  if (docker.context) argv.push('--context', docker.context);
+  if (docker.daemonHost) argv.push('-H', docker.daemonHost);
+  return argv;
+}
+
+export interface DockerDriftStatus {
+  /** Container exists (daemon reachable AND a container with this name is present). */
+  exists: boolean;
+  running: boolean;
+  /** The desired configHash no longer matches the container's codeman.confighash label. */
+  drifted: boolean;
+  currentHash?: string;
+}
+
+/**
+ * Drift check (docs/docker-cases-plan.md §4): compare the DESIRED configHash
+ * against the existing container's `codeman.confighash` label so docker-host
+ * config edits actually take effect instead of being silently ignored by the
+ * idempotent inspect-or-create launch chain. `exists:false` (no container /
+ * daemon down) means there is nothing to drift. No-op under VITEST.
+ */
+export async function checkDockerConfigDrift(
+  docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost' | 'containerName' | 'configHash'>
+): Promise<DockerDriftStatus> {
+  if (IS_TEST_MODE) return { exists: false, running: false, drifted: false };
+  const argv = dockerEngineArgv(docker);
+  try {
+    const { stdout } = await execFileAsync(
+      argv[0],
+      [
+        ...argv.slice(1),
+        'inspect',
+        '-f',
+        '{{.State.Running}}\t{{index .Config.Labels "codeman.confighash"}}',
+        docker.containerName,
+      ],
+      { timeout: DOCKER_PROBE_TIMEOUT_MS }
+    );
+    const [running = '', hash = ''] = stdout.trim().split('\t');
+    return { exists: true, running: running === 'true', drifted: hash !== docker.configHash, currentHash: hash };
+  } catch {
+    return { exists: false, running: false, drifted: false };
+  }
+}
+
+/**
+ * `docker rm -f` the case container (the recreate-on-drift confirm action; the
+ * launch chain recreates it with the new config on next start). Workspace +
+ * transcripts ride bind mounts and survive; the conversation resumes via the
+ * case's lastClaudeSessionId. No-op under VITEST.
+ */
+export async function removeDockerContainer(
+  docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost' | 'containerName'>
+): Promise<void> {
+  if (IS_TEST_MODE) return;
+  const argv = dockerEngineArgv(docker);
+  await execFileAsync(argv[0], [...argv.slice(1), 'rm', '-f', docker.containerName], { timeout: 30_000 });
+}
+
 export interface DockerAvailability {
   ok: boolean;
   engine: DockerEngine;
@@ -497,11 +788,16 @@ export async function checkDockerAvailable(engine?: DockerEngine): Promise<Docke
   };
 }
 
-/** Is the base image present locally? (never triggers an auto-pull). */
-export async function checkDockerImagePresent(engine: DockerEngine, image: string): Promise<boolean> {
+/** Is the base image present on the host's daemon? (never triggers an auto-pull).
+ *  Honors context/daemonHost so a remote-daemon host is probed on the RIGHT daemon. */
+export async function checkDockerImagePresent(
+  docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost'>,
+  image: string
+): Promise<boolean> {
   if (IS_TEST_MODE) return true;
+  const argv = dockerEngineArgv(docker);
   try {
-    await execFileAsync(engine, ['image', 'inspect', '--format', '{{.Id}}', image], {
+    await execFileAsync(argv[0], [...argv.slice(1), 'image', 'inspect', '--format', '{{.Id}}', image], {
       timeout: DOCKER_PROBE_TIMEOUT_MS,
     });
     return true;
@@ -510,6 +806,108 @@ export async function checkDockerImagePresent(engine: DockerEngine, image: strin
   }
 }
 
+export interface EnsureImageResult {
+  ok: boolean;
+  /** true when this call actually ran a build (vs. the image already existing). */
+  built: boolean;
+  alreadyPresent: boolean;
+  error?: string;
+}
+
+/** In-flight builds keyed by `engine:image`, so concurrent callers share ONE build. */
+const inFlightImageBuilds = new Map<string, Promise<EnsureImageResult>>();
+
+/**
+ * Resolve the repo's Dockerfile + build context. Works from BOTH src (dev/tsx) and
+ * dist/index.js (esbuild prod: dist sits at repo root), since both are one level
+ * under the repo root. Returns null when the Dockerfile is absent (npm-global
+ * installs don't ship docker/ — Docker cases are a git-clone feature).
+ */
+function resolveAgentDockerfile(): { dockerfile: string; contextDir: string } | null {
+  const repoRoot = join(dirname(fileURLToPath(import.meta.url)), '..');
+  const dockerfile = join(repoRoot, 'docker', 'agent.Dockerfile');
+  return existsSync(dockerfile) ? { dockerfile, contextDir: repoRoot } : null;
+}
+
+/**
+ * Ensure the agent base image exists, BUILDING it locally on first use so a missing
+ * image is never a hard blocker (decision: "build locally on first use",
+ * docs/docker-cases-plan.md). Idempotent, concurrency-safe (one build per
+ * engine:image shared by concurrent callers), and a no-op under VITEST. Only the
+ * DEFAULT image is auto-built — we can never build a user's custom ref, and the
+ * `--pull=never` invariant forbids pulling. `onProgress` receives build output
+ * lines for SSE surfacing.
+ */
+export async function ensureAgentBaseImage(
+  docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost'>,
+  image: string,
+  opts: { onProgress?: (line: string) => void; noCache?: boolean } = {}
+): Promise<EnsureImageResult> {
+  if (IS_TEST_MODE) return { ok: true, built: false, alreadyPresent: true };
+  if (await checkDockerImagePresent(docker, image)) {
+    return { ok: true, built: false, alreadyPresent: true };
+  }
+  if (image !== DEFAULT_AGENT_IMAGE) {
+    return {
+      ok: false,
+      built: false,
+      alreadyPresent: false,
+      error: `image ${image} is not present and only ${DEFAULT_AGENT_IMAGE} is auto-built. Build or pull ${image} yourself.`,
+    };
+  }
+  const key = `${docker.engine}:${image}`;
+  const existing = inFlightImageBuilds.get(key);
+  if (existing) return existing;
+  const build = buildAgentImage(docker, image, opts).finally(() => inFlightImageBuilds.delete(key));
+  inFlightImageBuilds.set(key, build);
+  return build;
+}
+
+function buildAgentImage(
+  docker: Pick<SessionDocker, 'engine' | 'context' | 'daemonHost'>,
+  image: string,
+  opts: { onProgress?: (line: string) => void; noCache?: boolean }
+): Promise<EnsureImageResult> {
+  const resolved = resolveAgentDockerfile();
+  if (!resolved) {
+    return Promise.resolve({
+      ok: false,
+      built: false,
+      alreadyPresent: false,
+      error: `docker/agent.Dockerfile not found in this install; clone the repo or build ${image} manually`,
+    });
+  }
+  const argv = dockerEngineArgv(docker);
+  const args = [
+    ...argv.slice(1),
+    ...agentImageBuildArgs(resolved.dockerfile, image, resolved.contextDir, opts.noCache),
+  ];
+  return new Promise<EnsureImageResult>((resolve) => {
+    // async spawn (NEVER spawnSync) so a multi-minute build never wedges the event loop.
+    const child = spawn(argv[0], args, { stdio: ['ignore', 'pipe', 'pipe'] });
+    const forward = (buf: Buffer) => {
+      for (const line of buf.toString('utf-8').split('\n')) {
+        const trimmed = line.trimEnd();
+        if (trimmed) opts.onProgress?.(trimmed);
+      }
+    };
+    child.stdout?.on('data', forward);
+    child.stderr?.on('data', forward);
+    child.on('error', (err) => {
+      resolve({
+        ok: false,
+        built: false,
+        alreadyPresent: false,
+        error: `could not spawn ${argv[0]} build: ${err.message}`,
+      });
+    });
+    child.on('exit', (code) => {
+      if (code === 0) resolve({ ok: true, built: true, alreadyPresent: false });
+      else resolve({ ok: false, built: false, alreadyPresent: false, error: `${argv[0]} build failed (exit ${code})` });
+    });
+  });
+}
+
 export interface DockerTmuxCheckResult {
   ok: boolean;
   tmuxPath?: string;
@@ -524,21 +922,21 @@ export interface DockerTmuxCheckResult {
  * (`--pull=never`). No-op under VITEST. Mirror of checkRemoteTmuxAvailable.
  */
 export async function checkDockerTmuxAvailable(
-  docker: Pick<SessionDocker, 'engine' | 'image'>
+  docker: Pick<SessionDocker, 'engine' | 'image' | 'context' | 'daemonHost'>
 ): Promise<DockerTmuxCheckResult> {
   if (IS_TEST_MODE) return { ok: true, tmuxPath: '/usr/bin/tmux' };
-  const engine = docker.engine;
-  if (!(await checkDockerImagePresent(engine, docker.image))) {
+  if (!(await checkDockerImagePresent(docker, docker.image))) {
     return {
       ok: false,
       imageMissing: true,
-      error: `base image ${docker.image} not present: build it with 'node scripts/build-agent-image.mjs' (or pull it)`,
+      error: `image ${docker.image} not present (the default image is auto-built on first use; a custom image must be built or pulled first)`,
     };
   }
+  const argv = dockerEngineArgv(docker);
   try {
     const { stdout } = await execFileAsync(
-      engine,
-      ['run', '--rm', '--pull=never', docker.image, 'sh', '-lc', 'command -v tmux'],
+      argv[0],
+      [...argv.slice(1), 'run', '--rm', '--pull=never', docker.image, 'sh', '-lc', 'command -v tmux'],
       { timeout: DOCKER_PROBE_TIMEOUT_MS }
     );
     const tmuxPath = stdout.trim();
@@ -635,16 +1033,21 @@ export async function reapOrphanedDockerContainers(
  * Returns undefined on any failure. No-op under VITEST.
  */
 export async function probeDockerCliVersion(
-  docker: Pick<SessionDocker, 'engine' | 'containerName'>,
+  docker: Pick<SessionDocker, 'engine' | 'containerName' | 'context' | 'daemonHost'>,
   mode: SessionMode
 ): Promise<string | undefined> {
   if (IS_TEST_MODE) return undefined;
   const bin = mode === 'shell' ? null : mode;
   if (!bin) return undefined;
+  const argv = dockerEngineArgv(docker);
   try {
-    const { stdout } = await execFileAsync(docker.engine, ['exec', docker.containerName, bin, '--version'], {
-      timeout: DOCKER_PROBE_TIMEOUT_MS,
-    });
+    const { stdout } = await execFileAsync(
+      argv[0],
+      [...argv.slice(1), 'exec', docker.containerName, bin, '--version'],
+      {
+        timeout: DOCKER_PROBE_TIMEOUT_MS,
+      }
+    );
     const match = stdout.trim().match(/\d+\.\d+\.\d+/);
     return match ? match[0] : stdout.trim() || undefined;
   } catch {

src/hooks-config.ts

@@ -16,9 +16,9 @@
  * `stop`, `teammate_idle`, `task_completed`
  *
  * Hook categories: `Notification` (3 matchers), `Stop` (1), `TeammateIdle` (1),
- * `TaskCompleted` (1)
+ * `TaskCompleted` (1), `PostToolUse` (1 self-contained background Bash rewake)
  *
- * @dependencies types (HookEventType), config/auth-config (HOOK_TIMEOUT_MS)
+ * @dependencies types (HookEventType), config/auth-config (HOOK_TIMEOUT_SECONDS)
  * @consumedby web/server (session creation), session-cli-builder (env setup)
  *
  * @module hooks-config
@@ -29,7 +29,7 @@ import { readFile, writeFile, mkdir } from 'node:fs/promises';
 import { join } from 'node:path';
 
 import type { HookEventType } from './types.js';
-import { HOOK_TIMEOUT_MS } from './config/auth-config.js';
+import { HOOK_TIMEOUT_SECONDS } from './config/auth-config.js';
 
 /**
  * Serializes read-modify-write access to a `settings.local.json` path. Every
@@ -40,6 +40,104 @@ import { HOOK_TIMEOUT_MS } from './config/auth-config.js';
  * are independent; the map self-prunes when a path's chain goes idle.
  */
 const settingsWriteLocks = new Map<string, Promise<unknown>>();
+/**
+ * Version-agnostic ownership prefix: every rewake script version embeds a marker
+ * starting with this, and `isCodemanHookHandler` matches on the prefix. That way a
+ * version bump replaces the old handler instead of duplicating it (matching on the
+ * full versioned marker would disown every older script).
+ */
+const BACKGROUND_WAKE_MARKER_PREFIX = 'CODEMAN_BACKGROUND_REWAKE_V';
+/**
+ * Current script version. Bump the suffix whenever `generateBackgroundWakeScript`
+ * changes: `refreshStaleCodemanHooks` treats the absence of the CURRENT marker as
+ * stale, so healed cases pick up the new script on next launch.
+ */
+const BACKGROUND_WAKE_MARKER = `${BACKGROUND_WAKE_MARKER_PREFIX}2`;
+const BACKGROUND_WAKE_TIMEOUT_SECONDS = 6 * 60 * 60;
+
+/**
+ * Inline Node helper for Claude Code's `asyncRewake` hook.
+ *
+ * A background Bash tool returns immediately with a task ID, then Claude writes
+ * its completion as a queue-operation in the transcript. Watching that durable
+ * record avoids injecting terminal input (which could submit a user's draft).
+ * The helper is embedded in settings via `node -e`, so it has no script path
+ * that can go stale after an install or plugin-cache cleanup.
+ *
+ * Self-terminating: Claude Code enforces the hook timeout, but the helper does not
+ * rely on it. It exits on its own deadline (same budget) and when orphaned
+ * (`ppid === 1`), so a dead session cannot leave a poller stat-ing the transcript
+ * forever. The ppid check misses subreaper setups; the deadline is the backstop.
+ */
+export function generateBackgroundWakeScript(): string {
+  return [
+    "const fs = require('node:fs');",
+    `const ${BACKGROUND_WAKE_MARKER} = true;`,
+    `const deadline = Date.now() + ${BACKGROUND_WAKE_TIMEOUT_SECONDS} * 1000;`,
+    'let input = {};',
+    "try { input = JSON.parse(fs.readFileSync(0, 'utf8') || '{}'); } catch { process.exit(0); }",
+    'function findTaskId(value) {',
+    "  const idKeys = new Set(['taskId', 'task_id', 'shellId', 'shell_id', 'backgroundTaskId', 'background_task_id']);",
+    '  const stack = [value];',
+    '  const seen = new Set();',
+    '  while (stack.length > 0) {',
+    '    const current = stack.pop();',
+    "    if (!current || typeof current !== 'object' || seen.has(current)) continue;",
+    '    seen.add(current);',
+    '    for (const [key, nested] of Object.entries(current)) {',
+    "      if (idKeys.has(key) && typeof nested === 'string' && /^[A-Za-z0-9_-]+$/.test(nested)) return nested;",
+    "      if (nested && typeof nested === 'object') stack.push(nested);",
+    '    }',
+    '  }',
+    "  const serialized = JSON.stringify(value ?? '');",
+    '  const messageMatch = serialized.match(/Command running in background with ID:\\s*([A-Za-z0-9_-]+)/i);',
+    '  if (messageMatch) return messageMatch[1];',
+    '  const pathMatch = serialized.match(/[\\\\/]tasks[\\\\/]([A-Za-z0-9_-]+)\\.output/i);',
+    '  return pathMatch ? pathMatch[1] : null;',
+    '}',
+    'const taskId = findTaskId(input.tool_response);',
+    "const transcriptPath = typeof input.transcript_path === 'string' ? input.transcript_path : '';",
+    'if (!taskId || !transcriptPath) process.exit(0);',
+    'let position = 0;',
+    'try { position = Math.max(0, fs.statSync(transcriptPath).size - 262144); } catch { process.exit(0); }',
+    "let carry = '';",
+    'function inspect(text) {',
+    '  for (const line of text.split(/\\r?\\n/)) {',
+    '    if (!line.includes(taskId)) continue;',
+    '    let entry;',
+    '    try { entry = JSON.parse(line); } catch { continue; }',
+    "    if (entry.type !== 'queue-operation' || typeof entry.content !== 'string') continue;",
+    "    if (!entry.content.includes('<task-id>' + taskId + '</task-id>')) continue;",
+    '    const status = entry.content.match(/<status>(completed|failed|killed|error)<\\/status>/i);',
+    '    if (!status) continue;',
+    '    const output = entry.content.match(/<output-file>([^<]+)<\\/output-file>/i);',
+    "    const location = output ? ' Read ' + output[1] + ' and' : '';",
+    "    console.error('Background command ' + taskId + ' ' + status[1].toLowerCase() + '.' + location + ' continue the task.');",
+    '    process.exit(2);',
+    '  }',
+    '}',
+    'function poll() {',
+    '  if (Date.now() > deadline || process.ppid === 1) process.exit(0);',
+    '  try {',
+    '    const size = fs.statSync(transcriptPath).size;',
+    "    if (size < position) { position = 0; carry = ''; }",
+    '    if (size > position) {',
+    '      const length = Math.min(size - position, 1048576);',
+    '      const buffer = Buffer.allocUnsafe(length);',
+    "      const fd = fs.openSync(transcriptPath, 'r');",
+    '      const bytes = fs.readSync(fd, buffer, 0, length, position);',
+    '      fs.closeSync(fd);',
+    '      position += bytes;',
+    "      carry = (carry + buffer.subarray(0, bytes).toString('utf8')).slice(-262144);",
+    '      inspect(carry);',
+    '    }',
+    '  } catch {}',
+    '  setTimeout(poll, 1000);',
+    '}',
+    'poll();',
+  ].join('\n');
+}
+
 function withSettingsLock<T>(path: string, fn: () => Promise<T>): Promise<T> {
   const prev = settingsWriteLocks.get(path) ?? Promise.resolve();
   const run = prev.then(fn, fn); // run after the prior writer, regardless of its outcome
@@ -86,36 +184,118 @@ export function generateHooksConfig(): { hooks: Record<string, unknown[]> } {
       Notification: [
         {
           matcher: 'idle_prompt',
-          hooks: [{ type: 'command', command: curlCmd('idle_prompt'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('idle_prompt'), timeout: HOOK_TIMEOUT_SECONDS }],
         },
         {
           matcher: 'permission_prompt',
-          hooks: [{ type: 'command', command: curlCmd('permission_prompt'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('permission_prompt'), timeout: HOOK_TIMEOUT_SECONDS }],
         },
         {
           matcher: 'elicitation_dialog',
-          hooks: [{ type: 'command', command: curlCmd('elicitation_dialog'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('elicitation_dialog'), timeout: HOOK_TIMEOUT_SECONDS }],
         },
       ],
       Stop: [
         {
-          hooks: [{ type: 'command', command: curlCmd('stop'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('stop'), timeout: HOOK_TIMEOUT_SECONDS }],
         },
       ],
       TeammateIdle: [
         {
-          hooks: [{ type: 'command', command: curlCmd('teammate_idle'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('teammate_idle'), timeout: HOOK_TIMEOUT_SECONDS }],
         },
       ],
       TaskCompleted: [
         {
-          hooks: [{ type: 'command', command: curlCmd('task_completed'), timeout: HOOK_TIMEOUT_MS }],
+          hooks: [{ type: 'command', command: curlCmd('task_completed'), timeout: HOOK_TIMEOUT_SECONDS }],
+        },
+      ],
+      PostToolUse: [
+        {
+          matcher: 'Bash',
+          hooks: [
+            {
+              type: 'command',
+              command: 'node',
+              args: ['-e', generateBackgroundWakeScript()],
+              asyncRewake: true,
+              timeout: BACKGROUND_WAKE_TIMEOUT_SECONDS,
+            },
+          ],
         },
       ],
     },
   };
 }
 
+function isCodemanHookHandler(value: unknown): boolean {
+  try {
+    const serialized = JSON.stringify(value);
+    // Prefix, not the versioned marker: older script versions must still be ours.
+    return serialized.includes('/api/hook-event') || serialized.includes(BACKGROUND_WAKE_MARKER_PREFIX);
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Replace only Codeman-owned command handlers while preserving user events,
+ * matcher entries, and sibling handlers in mixed entries.
+ */
+function mergeCodemanHooks(existingValue: unknown, generated: Record<string, unknown[]>): Record<string, unknown[]> {
+  const existing =
+    existingValue && typeof existingValue === 'object' && !Array.isArray(existingValue)
+      ? (existingValue as Record<string, unknown>)
+      : {};
+  const merged: Record<string, unknown[]> = {};
+
+  for (const eventName of new Set([...Object.keys(existing), ...Object.keys(generated)])) {
+    const existingEntries = Array.isArray(existing[eventName]) ? (existing[eventName] as unknown[]) : [];
+    const generatedEntries = generated[eventName];
+    if (!generatedEntries) {
+      merged[eventName] = existingEntries;
+      continue;
+    }
+
+    const entries: unknown[] = [];
+    let insertedGenerated = false;
+    for (const entry of existingEntries) {
+      if (!entry || typeof entry !== 'object' || Array.isArray(entry)) {
+        if (!isCodemanHookHandler(entry)) entries.push(entry);
+        continue;
+      }
+
+      const record = entry as Record<string, unknown>;
+      if (!Array.isArray(record.hooks)) {
+        if (isCodemanHookHandler(record)) {
+          if (!insertedGenerated) {
+            entries.push(...generatedEntries);
+            insertedGenerated = true;
+          }
+        } else {
+          entries.push(entry);
+        }
+        continue;
+      }
+
+      const retainedHandlers = record.hooks.filter((handler) => !isCodemanHookHandler(handler));
+      const removedCodemanHandler = retainedHandlers.length !== record.hooks.length;
+      if (removedCodemanHandler && !insertedGenerated) {
+        entries.push(...generatedEntries);
+        insertedGenerated = true;
+      }
+      if (retainedHandlers.length > 0 || !removedCodemanHandler) {
+        entries.push(retainedHandlers.length === record.hooks.length ? entry : { ...record, hooks: retainedHandlers });
+      }
+    }
+
+    if (!insertedGenerated) entries.push(...generatedEntries);
+    merged[eventName] = entries;
+  }
+
+  return merged;
+}
+
 /**
  * Remove a subset of env keys from .claude/settings.local.json.env if present.
  * Used during the disk→tmux-setenv migration: when the caller is actively setting
@@ -237,29 +417,31 @@ export async function writeHooksConfig(casePath: string): Promise<void> {
     }
 
     const hooksConfig = generateHooksConfig();
-    const merged = { ...existing, ...hooksConfig };
+    const merged = {
+      ...existing,
+      hooks: mergeCodemanHooks(existing.hooks, hooksConfig.hooks),
+    };
 
     await writeFile(settingsPath, JSON.stringify(merged, null, 2) + '\n');
   });
 }
 
 /**
- * Self-heal a case's hooks block so the COD-91 unconditional hook-secret gate keeps
- * accepting its hook events.
+ * Self-heal a case's Codeman-owned hooks block.
  *
  * `writeHooksConfig` only runs when a case is first CREATED. Cases created before the
  * X-Codeman-Hook-Secret header was added (COD-54, 2026-06-10) keep hook curls in their
  * settings.local.json that POST to /api/hook-event WITHOUT the secret — which, once the
- * gate requires it unconditionally (COD-91), silently 401 on a password-protected
- * install. This refreshes the hooks block so those stale curls regain the header.
+ * gate requires it unconditionally (COD-91), silently 401 on a password-protected install.
+ * Older Codeman blocks also lack the background Bash async-rewake hook. Refresh either
+ * stale shape on launch so existing cases gain both current behaviors.
  *
  * Deliberately surgical: regenerates ONLY when settings.local.json already contains
- * Codeman's own hook curls (they target `/api/hook-event`) that lack the secret header.
- * No-op when the file/hooks are absent (we never impose hooks on a user who removed
- * them), when the hooks aren't ours, or when the secret is already present — so it never
- * clobbers a user's customizations and is cheap enough to call on every Claude spawn.
+ * Codeman's own hook curls (they target `/api/hook-event`) and they are stale. No-op
+ * when the file/hooks are absent (we never impose hooks on a user who removed them) or
+ * when the hooks aren't ours, so it is cheap enough to call on every Claude spawn.
  */
-export async function refreshStaleHookSecret(casePath: string): Promise<void> {
+export async function refreshStaleCodemanHooks(casePath: string): Promise<void> {
   const settingsPath = join(casePath, '.claude', 'settings.local.json');
   if (!existsSync(settingsPath)) return;
   await withSettingsLock(settingsPath, async () => {
@@ -274,8 +456,13 @@ export async function refreshStaleHookSecret(casePath: string): Promise<void> {
     // The generated curl carries this header literal (see generateHooksConfig); its
     // absence on our own hooks means they predate COD-54 and need regenerating.
     const hasSecret = hooksJson.includes('X-Codeman-Hook-Secret');
-    if (!isOurs || hasSecret) return;
-    const merged = { ...existing, ...generateHooksConfig() };
+    const hasBackgroundWake = hooksJson.includes(BACKGROUND_WAKE_MARKER);
+    if (!isOurs || (hasSecret && hasBackgroundWake)) return;
+    const generated = generateHooksConfig();
+    const merged = {
+      ...existing,
+      hooks: mergeCodemanHooks(existing.hooks, generated.hooks),
+    };
     await writeFile(settingsPath, JSON.stringify(merged, null, 2) + '\n');
   });
 }

src/mux-interface.ts

@@ -17,6 +17,7 @@ import type {
   CodexConfig,
   EffortLevel,
   GeminiConfig,
+  AntigravityConfig,
   SessionRemote,
   SessionDocker,
 } from './types.js';
@@ -39,6 +40,8 @@ export interface MuxSession {
   remote?: SessionRemote;
   /** Docker execution metadata for local tmux sessions wrapping `docker exec` */
   docker?: SessionDocker;
+  /** Owning username in multi-user mode (round-tripped through recovery like remote/docker) */
+  owner?: string;
   /** Session mode */
   mode: SessionMode;
   /** Whether webserver is attached to this session */
@@ -72,6 +75,7 @@ export interface CreateSessionOptions {
   openCodeConfig?: OpenCodeConfig;
   codexConfig?: CodexConfig;
   geminiConfig?: GeminiConfig;
+  antigravityConfig?: AntigravityConfig;
   /** When restoring after reboot, resume a previous Claude conversation by its session ID */
   resumeSessionId?: string;
   /** Extra env vars exported before launching the CLI (e.g., CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS). Ephemeral — not written to disk. */
@@ -84,6 +88,8 @@ export interface CreateSessionOptions {
   remote?: SessionRemote;
   /** Docker execution metadata for local tmux sessions wrapping `docker exec` */
   docker?: SessionDocker;
+  /** Owning username in multi-user mode; persisted for recovery. */
+  owner?: string;
 }
 
 /** Options for respawning a dead pane. */
@@ -98,6 +104,7 @@ export interface RespawnPaneOptions {
   openCodeConfig?: OpenCodeConfig;
   codexConfig?: CodexConfig;
   geminiConfig?: GeminiConfig;
+  antigravityConfig?: AntigravityConfig;
   /** Resume a previous Claude conversation when respawning */
   resumeSessionId?: string;
   /** Extra env vars exported before launching the CLI (preserved across respawns). */
@@ -110,6 +117,8 @@ export interface RespawnPaneOptions {
   remote?: SessionRemote;
   /** Docker execution metadata for local tmux sessions wrapping `docker exec` */
   docker?: SessionDocker;
+  /** Owning username (multi-user); redundant on respawn since the Session object survives, kept for shape parity. */
+  owner?: string;
 }
 
 /** Options for pane buffer capture (COD-47 full-history mode). */

src/plan-orchestrator.ts

@@ -20,7 +20,7 @@ import type { TerminalMultiplexer } from './mux-interface.js';
 import { existsSync, mkdirSync, writeFileSync } from 'node:fs';
 import { join } from 'node:path';
 import { RESEARCH_AGENT_PROMPT, PLANNER_PROMPT } from './prompts/index.js';
-import { getErrorMessage, type PlanItem } from './types.js';
+import { getErrorMessage, type PlanItem, type ClaudeMode } from './types.js';
 
 // Re-export for backward compatibility
 export type { PlanItem };
@@ -130,18 +130,28 @@ export class PlanOrchestrator {
   private taskDescription = '';
   private researchModel: string;
   private plannerModel: string;
+  // Multi-user permission threading: the resolved claudeMode/owner/allowedTools for the
+  // internal research/planner one-shots. Left undefined = today's single-user behavior
+  // (the caller threads the resolved global mode, byte-identical when !isMultiUserMode()).
+  private claudeMode?: ClaudeMode;
+  private owner?: string;
+  private allowedTools?: string;
 
   constructor(
     mux: TerminalMultiplexer,
     workingDir: string = process.cwd(),
     outputDir?: string,
-    modelConfig?: { defaultModel?: string; agentTypeOverrides?: Record<string, string> }
+    modelConfig?: { defaultModel?: string; agentTypeOverrides?: Record<string, string> },
+    security?: { claudeMode?: ClaudeMode; owner?: string; allowedTools?: string }
   ) {
     this.mux = mux;
     this.workingDir = workingDir;
     this.outputDir = outputDir;
     this.researchModel = modelConfig?.agentTypeOverrides?.explore || modelConfig?.defaultModel || DEFAULT_MODEL;
     this.plannerModel = modelConfig?.agentTypeOverrides?.review || modelConfig?.defaultModel || DEFAULT_MODEL;
+    this.claudeMode = security?.claudeMode;
+    this.owner = security?.owner;
+    this.allowedTools = security?.allowedTools;
   }
 
   private saveAgentOutput(agentType: string, prompt: string, result: unknown, durationMs: number): void {
@@ -424,6 +434,12 @@ export class PlanOrchestrator {
       mux: this.mux,
       useMux: false,
       mode: 'claude',
+      // Section 6.3: run this one-shot under the caller-resolved permission mode/owner so a
+      // non-granted multi-user user cannot regain --dangerously-skip-permissions. Undefined
+      // (single-user, not threaded) is byte-identical to today (Session keeps its default).
+      claudeMode: this.claudeMode,
+      allowedTools: this.allowedTools,
+      owner: this.owner,
     });
 
     this.runningSessions.add(session);
@@ -580,6 +596,10 @@ export class PlanOrchestrator {
       mux: this.mux,
       useMux: false,
       mode: 'claude',
+      // Section 6.3: same permission-mode/owner threading as the research one-shot above.
+      claudeMode: this.claudeMode,
+      allowedTools: this.allowedTools,
+      owner: this.owner,
     });
 
     this.runningSessions.add(session);

src/push-store.ts

@@ -9,10 +9,23 @@
 import { existsSync, readFileSync, writeFileSync, mkdirSync } from 'node:fs';
 import { join } from 'node:path';
 import webpush from 'web-push';
-import type { VapidKeys, PushSubscriptionRecord } from './types.js';
+import type { VapidKeys, PushSubscriptionRecord, UserRole } from './types.js';
 import { Debouncer } from './utils/index.js';
 import { getDataDir } from './config/instance.js';
 
+/**
+ * A push subscription plus the multi-user owner identity stamped at subscribe time.
+ * `username`/`role` are undefined in single-user mode (and for legacy records saved
+ * before this field existed). sendPushNotifications uses them to scope a
+ * session-notification to its owner's devices (+ admins) instead of fanning out to
+ * every user. Kept as a store-local widening of PushSubscriptionRecord so the shared
+ * type stays untouched; the extra keys serialize/persist transparently.
+ */
+export type OwnedPushSubscriptionRecord = PushSubscriptionRecord & {
+  username?: string;
+  role?: UserRole;
+};
+
 const DATA_DIR = getDataDir();
 const KEYS_FILE = join(DATA_DIR, 'push-keys.json');
 const SUBS_FILE = join(DATA_DIR, 'push-subscriptions.json');
@@ -20,7 +33,7 @@ const SAVE_DEBOUNCE_MS = 500;
 
 export class PushSubscriptionStore {
   private vapidKeys: VapidKeys | null = null;
-  private subscriptions: Map<string, PushSubscriptionRecord> = new Map();
+  private subscriptions: Map<string, OwnedPushSubscriptionRecord> = new Map();
   private saveDeb = new Debouncer(SAVE_DEBOUNCE_MS);
   private _disposed = false;
 
@@ -67,17 +80,19 @@ export class PushSubscriptionStore {
   }
 
   /** Register or update a push subscription (deduplicates by endpoint) */
-  addSubscription(sub: Omit<PushSubscriptionRecord, 'lastUsedAt'>): PushSubscriptionRecord {
+  addSubscription(sub: Omit<OwnedPushSubscriptionRecord, 'lastUsedAt'>): OwnedPushSubscriptionRecord {
     // Check for existing subscription with same endpoint
     for (const [existingId, existing] of this.subscriptions) {
       if (existing.endpoint === sub.endpoint) {
-        // Update existing
-        const updated: PushSubscriptionRecord = {
+        // Update existing (re-stamp owner identity so it tracks the current caller)
+        const updated: OwnedPushSubscriptionRecord = {
           ...existing,
           keys: sub.keys,
           userAgent: sub.userAgent,
           lastUsedAt: Date.now(),
           pushPreferences: sub.pushPreferences,
+          username: sub.username,
+          role: sub.role,
         };
         this.subscriptions.set(existingId, updated);
         this.scheduleSave();
@@ -86,7 +101,7 @@ export class PushSubscriptionStore {
     }
 
     // New subscription
-    const record: PushSubscriptionRecord = {
+    const record: OwnedPushSubscriptionRecord = {
       ...sub,
       lastUsedAt: Date.now(),
     };
@@ -96,7 +111,7 @@ export class PushSubscriptionStore {
   }
 
   /** Update push preferences for a subscription */
-  updatePreferences(id: string, preferences: Record<string, boolean>): PushSubscriptionRecord | null {
+  updatePreferences(id: string, preferences: Record<string, boolean>): OwnedPushSubscriptionRecord | null {
     const sub = this.subscriptions.get(id);
     if (!sub) return null;
     sub.pushPreferences = preferences;
@@ -124,12 +139,12 @@ export class PushSubscriptionStore {
   }
 
   /** Get all subscriptions */
-  getAll(): PushSubscriptionRecord[] {
+  getAll(): OwnedPushSubscriptionRecord[] {
     return Array.from(this.subscriptions.values());
   }
 
   /** Get a single subscription by ID */
-  get(id: string): PushSubscriptionRecord | null {
+  get(id: string): OwnedPushSubscriptionRecord | null {
     return this.subscriptions.get(id) ?? null;
   }
 
@@ -138,7 +153,7 @@ export class PushSubscriptionStore {
     if (!existsSync(SUBS_FILE)) return;
     try {
       const raw = readFileSync(SUBS_FILE, 'utf-8');
-      const arr = JSON.parse(raw) as PushSubscriptionRecord[];
+      const arr = JSON.parse(raw) as OwnedPushSubscriptionRecord[];
       for (const sub of arr) {
         this.subscriptions.set(sub.id, sub);
       }

src/remote-hosts.ts

@@ -8,6 +8,7 @@ import type {
   RemoteCase,
   RemoteCommandMode,
   RemoteHost,
+  RemoteSessionInfo,
   RemoteSshOptions,
   SessionMode,
   SessionRemote,
@@ -57,16 +58,61 @@ export async function writeRemoteCases(configDir: string, cases: RemoteCase[]):
   await writeJsonArray(configDir, remoteCasesPath(configDir), cases);
 }
 
+/**
+ * The remote user's login shell, defaulted and quoted.
+ *
+ * The default is belt-and-braces, not a live bug: an empty `$SHELL` would expand
+ * to `exec  -i -l`, which the shell reads as `exec -i` — "not found", pane dead on
+ * arrival, the #208 failure all over again (verified: `sh -c 'exec $SHELL -i -l'`
+ * with SHELL unset prints `exec: -i: not found`). In practice tmux always exports
+ * SHELL into a pane from its own `default-shell` option, so the command as USED
+ * here is safe either way (also verified). The default matters because these
+ * strings are the seed values a per-host `commands.*` override is edited from, and
+ * nothing constrains where an edited one ends up running. Quoted for a shell path
+ * containing spaces. `/bin/sh` exists on every POSIX host.
+ */
+const REMOTE_LOGIN_SHELL = '"${SHELL:-/bin/sh}"';
+
+/**
+ * Run `command` through the remote user's interactive login shell, so per-user
+ * PATH entries (~/.local/bin, ~/.opencode/bin, …) are resolved before the CLI name
+ * is looked up. ssh's remote-command execution is neither interactive nor login,
+ * so a bare `exec claude` sees only sshd's minimal default PATH and dies with
+ * "command not found" (exit 127).
+ *
+ * Shells that take neither flag (nushell, elvish, …) cannot be detected from here
+ * the way `loginShellArgs()` detects them locally, since the shell is whatever the
+ * REMOTE passwd says. A host like that is what the per-host `commands.*` override
+ * is for.
+ */
+export function remoteLoginShellCommand(command: string): string {
+  return `exec ${REMOTE_LOGIN_SHELL} -i -l -c ${shellescape(command)}`;
+}
+
 export function defaultRemoteCommandForMode(mode: SessionMode): string {
+  // Agent CLIs (claude/opencode/codex/gemini/antigravity) are typically installed
+  // under per-user paths like ~/.local/bin or ~/.opencode/bin, added to PATH only by
+  // the remote user's interactive-login shell startup files (~/.zshrc etc.). ssh's
+  // remote-command execution is neither interactive nor login, so a bare `exec
+  // claude` sees only sshd's minimal default PATH and fails with "command not
+  // found" (exit 127) — confirmed via `tmux capture-pane` on the
+  // remain-on-exit-preserved dead pane. Route through `$SHELL -i -l -c`, the same
+  // fix already used for shell mode below, so PATH is fully resolved before the
+  // CLI name is looked up.
   const commands: Record<RemoteCommandMode, string> = {
-    shell: 'exec bash -l',
+    // $SHELL, not a hardcoded bash: sshd sets it from the remote user's
+    // /etc/passwd entry, so this launches their actual login shell (zsh,
+    // fish, etc.). -i -l so it sources rc files (~/.zshrc etc.), matching
+    // the local shell-mode launch.
+    shell: `exec ${REMOTE_LOGIN_SHELL} -i -l`,
     // Mirror the LOCAL claude default so the remote agent runs non-interactively
     // (no trust-folder/permission prompt that nothing on the remote answers). The
     // per-host `commands.claude` override stays the escape hatch.
-    claude: 'exec claude --dangerously-skip-permissions',
-    opencode: 'exec opencode',
-    codex: 'exec codex',
-    gemini: 'exec gemini',
+    claude: remoteLoginShellCommand('claude --dangerously-skip-permissions'),
+    opencode: remoteLoginShellCommand('opencode'),
+    codex: remoteLoginShellCommand('codex'),
+    gemini: remoteLoginShellCommand('gemini'),
+    antigravity: remoteLoginShellCommand('agy'),
   };
   return commands[mode as RemoteCommandMode] || commands.shell;
 }
@@ -173,6 +219,14 @@ export interface RemoteTmuxCheckResult {
 export async function checkRemoteTmuxAvailable(
   host: Pick<RemoteHost, 'username' | 'host' | 'port'> & RemoteSshOptions
 ): Promise<RemoteTmuxCheckResult> {
+  // Under vitest, never open a real ssh connection — mirrors TmuxManager's
+  // no-op-shell-under-VITEST (IS_TEST_MODE). Without this, remote-case
+  // create-path tests hit a real ~10s ssh timeout. The command construction is
+  // covered by buildRemoteTmuxCheckCommand unit tests; only the live probe is
+  // short-circuited here.
+  if (process.env.VITEST) {
+    return { ok: true, tmuxPath: '(test-mode)' };
+  }
   const command = buildRemoteTmuxCheckCommand(host);
   try {
     const { stdout } = await execAsync(command, { timeout: 15_000 });
@@ -202,6 +256,109 @@ export async function checkRemoteTmuxAvailable(
   }
 }
 
+/**
+ * COD-105 — build the SSH command that lists `codeman-*` tmux sessions on a
+ * remote host's canonical `-L codeman` socket.
+ *
+ * `list-sessions` exits NON-ZERO with empty output when no sessions exist (and
+ * the server isn't running), so `2>/dev/null` swallows tmux's "no server
+ * running" stderr; the caller treats a non-zero exit / empty output as "no
+ * sessions" rather than an error.
+ *
+ * COD-107 — connection options come from the shared `buildSshConnectionArgs`, so
+ * discovery connects with the SAME port/identity/proxy/jump-host as the launch
+ * and the tmux prereq probe.
+ */
+export function buildRemoteListSessionsCommand(
+  host: Pick<RemoteHost, 'username' | 'host' | 'port'> & RemoteSshOptions
+): string {
+  const [ssh, ...connectionArgs] = buildSshConnectionArgs(host);
+  const parts = [ssh, connectionArgs[0], '-o ConnectTimeout=10', ...connectionArgs.slice(1)];
+  // The tmux list-sessions invocation is passed as ONE shell-quoted argument so
+  // the remote login shell runs it verbatim. The `-F` format uses literal `\t`
+  // separators (tmux expands them); `2>/dev/null` is inside the quoted command.
+  const remoteCmd =
+    'tmux -L codeman list-sessions -F "#{session_name}\\t#{session_attached}\\t#{session_created}\\t#{session_windows}" 2>/dev/null';
+  parts.push(remoteSshTarget(host), shellescape(remoteCmd));
+  return parts.join(' ');
+}
+
+/**
+ * COD-105 — pure parser for the `tmux list-sessions -F` output emitted by
+ * `buildRemoteListSessionsCommand`. Factored out so the parse is unit-testable
+ * without opening a real ssh connection.
+ *
+ * - Splits each non-empty line into [name, attached, created, windows] on the
+ *   field separator. IMPORTANT: the remote tmux's `-F "…\t…"` format does NOT
+ *   expand `\t` to a real tab — it emits the LITERAL two-character sequence
+ *   `\t` (verified on aa-desktop / tmux next-3.7). So we split on the literal
+ *   backslash-t sequence; we also tolerate a real tab in case a tmux build
+ *   does expand it. (A real TAB is the regex `\t`; a literal backslash-t is the
+ *   regex `\\t`.)
+ * - Keeps ONLY sessions whose name starts with `codeman-` (ignores foreign tmux
+ *   sessions that happen to share the socket).
+ * - Coerces: `attached` → boolean (`'1'`), `created`/`windows` → finite ints.
+ * - Skips malformed lines (wrong column count or non-numeric created/windows)
+ *   rather than emitting garbage.
+ */
+export function parseRemoteSessionList(stdout: string): RemoteSessionInfo[] {
+  const out: RemoteSessionInfo[] = [];
+  for (const rawLine of stdout.split('\n')) {
+    const line = rawLine.trim();
+    if (!line) continue;
+    // Split on a literal `\t` (backslash + t, what the remote tmux emits) OR a
+    // real tab character. `/\\t|\t/` = the two-char sequence, or a TAB.
+    const cols = line.split(/\\t|\t/);
+    if (cols.length !== 4) continue;
+    const [name, attachedStr, createdStr, windowsStr] = cols;
+    if (!name.startsWith('codeman-')) continue;
+    const created = Number(createdStr);
+    const windows = Number(windowsStr);
+    if (!Number.isFinite(created) || !Number.isFinite(windows)) continue;
+    // COD-106 — `session_attached` is the CLIENT COUNT (not a 0/1 flag); >1 = shared.
+    const attachedNum = Number(attachedStr.trim());
+    const attachedClients = Number.isFinite(attachedNum) ? Math.max(0, Math.trunc(attachedNum)) : 0;
+    out.push({
+      name,
+      attached: attachedClients > 0,
+      attachedClients,
+      created: Math.trunc(created),
+      windows: Math.trunc(windows),
+    });
+  }
+  return out;
+}
+
+/**
+ * COD-105 — discover `codeman-*` tmux sessions already running on a remote host
+ * (created by the remote's own Codeman, another instance, or this one), so the
+ * operator can attach to one this Codeman didn't launch.
+ *
+ * NEVER throws: returns `[]` on unreachable host / no tmux / no sessions
+ * (`list-sessions` exits non-zero with empty output when there are none).
+ *
+ * VITEST guard — like `checkRemoteTmuxAvailable`, returns `[]` under test so a
+ * real ssh never runs in a request path (which would make route tests hit a
+ * ~10s timeout). The command construction is covered by
+ * `buildRemoteListSessionsCommand` and the parse by `parseRemoteSessionList`.
+ */
+export async function listRemoteCodemanSessions(
+  remote: Pick<RemoteHost, 'username' | 'host' | 'port'> & RemoteSshOptions
+): Promise<RemoteSessionInfo[]> {
+  if (process.env.VITEST) {
+    return [];
+  }
+  const command = buildRemoteListSessionsCommand(remote);
+  try {
+    const { stdout } = await execAsync(command, { timeout: 15_000 });
+    return parseRemoteSessionList(stdout);
+  } catch {
+    // Unreachable host, no tmux server, or no sessions (non-zero exit). All map
+    // to "nothing to attach to" — never surface as an error to the caller.
+    return [];
+  }
+}
+
 export function remoteDisplayPath(
   remote: Pick<SessionRemote, 'username' | 'host' | 'remotePath'> | { username: string; host: string; path: string }
 ): string {
@@ -218,6 +375,10 @@ export function toSessionRemote(host: RemoteHost, remoteCase: RemoteCase): Sessi
     port: host.port,
     remotePath: remoteCase.remotePath,
     commands: host.commands,
+    // COD-105 — the COD-104 launch path creates the remote session, so we own it
+    // (an explicit kill may propagate a remote kill-session). Discovered+attached
+    // sessions go through `toAttachedSessionRemote` with `owned: false`.
+    owned: true,
     // COD-107 — carry the advanced SSH options from host config into the session
     // so the launch/prereq commands connect the same way the operator configured.
     identityFile: host.identityFile,
@@ -226,3 +387,38 @@ export function toSessionRemote(host: RemoteHost, remoteCase: RemoteCase): Sessi
     extraSshOptions: host.extraSshOptions,
   };
 }
+
+/**
+ * COD-105 — build a NON-owned `SessionRemote` for ATTACHING to a `codeman-*`
+ * session already running on a remote host (discovered via
+ * `listRemoteCodemanSessions`). The resulting session's pane runs
+ * `tmux -L codeman attach -t <remoteSessionName>` (see
+ * `buildRemoteAttachCommand`), and because we did NOT create the remote session,
+ * `owned: false` means closing the tab DETACHES rather than killing it.
+ *
+ * `remotePath` is informational here (the attached remote session keeps its own
+ * cwd); we record the host's nominal path so display helpers still show
+ * `user@host:path`.
+ */
+export function toAttachedSessionRemote(
+  host: RemoteHost,
+  remoteSessionName: string,
+  remotePath: string
+): SessionRemote {
+  return {
+    hostId: host.id,
+    label: host.label,
+    host: host.host,
+    username: host.username,
+    port: host.port,
+    remotePath,
+    commands: host.commands,
+    // Discovered + attached — another Codeman created it. Detach-not-kill.
+    owned: false,
+    remoteSessionName,
+    identityFile: host.identityFile,
+    socksProxy: host.socksProxy,
+    jumpHost: host.jumpHost,
+    extraSshOptions: host.extraSshOptions,
+  };
+}

src/remote-reconnect.ts

@@ -0,0 +1,184 @@
+/**
+ * @fileoverview Pure logic for the remote-session auto-reconnect watcher (COD-108).
+ *
+ * COD-104 made remote tmux sessions durable + idempotently reattachable, but a
+ * reconnect only fired at explicit trigger points. COD-108 adds a continuous
+ * watcher (in `TmuxManager`) that detects a dead remote pane and emits
+ * `remoteSessionDropped`; `SessionManager`/server then reassembles the respawn
+ * options and reattaches (re-running the idempotent remote command).
+ *
+ * This module holds the SIDE-EFFECT-FREE pieces so they can be unit-tested
+ * without real tmux:
+ *  - the bounded exponential **backoff schedule** (attempt → delay, capped),
+ *  - the per-session **reconnect state** shape,
+ *  - the **eligibility decision** (`decideReconnect`) given a session + its
+ *    reconnect state + the current time + the guard set.
+ *
+ * The watcher in `tmux-manager.ts` owns the live `isPaneDead` probe and the
+ * timers; everything here is pure and deterministic (time is injected).
+ *
+ * @module remote-reconnect
+ */
+
+/**
+ * Bounded exponential backoff delays (ms) between reconnect attempts.
+ * Attempt N (1-based) waits `BACKOFF_SCHEDULE_MS[N-1]` from the previous emit
+ * before the next emit is eligible. After the last entry the session is
+ * considered `reconnect-exhausted` and the watcher stops emitting for it.
+ *
+ * 5s, 15s, 45s, 2m, 5m, 5m → ~6 attempts spanning ~13 minutes.
+ */
+export const BACKOFF_SCHEDULE_MS: readonly number[] = [5_000, 15_000, 45_000, 120_000, 300_000, 300_000];
+
+/** Maximum number of reconnect attempts before exhaustion. */
+export const MAX_RECONNECT_ATTEMPTS = BACKOFF_SCHEDULE_MS.length;
+
+/**
+ * Delay (ms) to wait AFTER emitting attempt `attempt` (1-based) before the next
+ * attempt is eligible. `attempt <= 0` returns the first delay; an attempt at or
+ * beyond the cap returns the last delay (callers should check exhaustion via
+ * {@link isExhausted} rather than relying on this for the stop decision).
+ *
+ * Pure — no clock, no I/O.
+ */
+export function reconnectDelayForAttempt(attempt: number): number {
+  if (!Number.isFinite(attempt) || attempt <= 1) return BACKOFF_SCHEDULE_MS[0];
+  const idx = Math.min(Math.floor(attempt) - 1, BACKOFF_SCHEDULE_MS.length - 1);
+  return BACKOFF_SCHEDULE_MS[idx];
+}
+
+/** Whether `attempts` reconnect emits have reached/exceeded the cap. Pure. */
+export function isExhausted(attempts: number): boolean {
+  return attempts >= MAX_RECONNECT_ATTEMPTS;
+}
+
+/**
+ * Per-session reconnect bookkeeping held by the watcher. All time values are
+ * epoch ms. `inFlight` guards against stacking respawns when a tick fires while
+ * a previous reattach is still running. `exhaustedEmitted` ensures the
+ * `remoteReconnectExhausted` event fires at most once per session.
+ */
+export interface RemoteReconnectState {
+  /** Number of `remoteSessionDropped` emits so far (advances per emit). */
+  attempts: number;
+  /** Earliest time (epoch ms) the next emit is eligible. 0 = eligible now. */
+  nextEligibleAt: number;
+  /** A reattach triggered by a prior emit is currently running. */
+  inFlight: boolean;
+  /** Cap reached — stop auto-retrying for this session. */
+  exhausted: boolean;
+  /** The `remoteReconnectExhausted` SSE event has already been emitted. */
+  exhaustedEmitted: boolean;
+}
+
+/** A fresh reconnect state (no attempts, immediately eligible). Pure. */
+export function freshReconnectState(): RemoteReconnectState {
+  return { attempts: 0, nextEligibleAt: 0, inFlight: false, exhausted: false, exhaustedEmitted: false };
+}
+
+/**
+ * Advance the backoff after an emit at time `now`. Increments `attempts` and
+ * schedules `nextEligibleAt = now + delay`. Returns a NEW state object (does
+ * not mutate the input). Pure.
+ *
+ * NOTE: this does NOT set `exhausted`. Exhaustion is a decision the watcher
+ * makes on the FOLLOWING tick (via {@link decideReconnect} → `exhaust`), so the
+ * `remoteReconnectExhausted` event fires exactly once after the final attempt's
+ * backoff window elapses — not pre-emptively on the last emit.
+ */
+export function advanceBackoff(state: RemoteReconnectState, now: number): RemoteReconnectState {
+  const attempts = state.attempts + 1;
+  const delay = reconnectDelayForAttempt(attempts);
+  return {
+    ...state,
+    attempts,
+    nextEligibleAt: now + delay,
+  };
+}
+
+/** Reset after a successful reattach — back to a fresh, eligible state. Pure. */
+export function resetReconnectState(): RemoteReconnectState {
+  return freshReconnectState();
+}
+
+/** Minimal session view the decision needs (avoids importing MuxSession here). */
+export interface ReconnectSessionView {
+  sessionId: string;
+  /** Truthy when this is a remote (SSH-wrapped) session. */
+  isRemote: boolean;
+  /** Result of `isPaneDead(muxName)` for this session. */
+  paneDead: boolean;
+}
+
+/**
+ * Decision outcomes for a single watcher tick on one session.
+ *  - `emit`     → emit `remoteSessionDropped { sessionId, attempt }`, then
+ *                 advance backoff (attempt = the returned `attempt`).
+ *  - `exhaust`  → cap reached this tick; emit `remoteReconnectExhausted` once.
+ *  - `skip`     → do nothing (not remote / pane alive / guarded / in-flight /
+ *                 not yet due / already exhausted).
+ */
+export type ReconnectAction =
+  | { kind: 'emit'; attempt: number }
+  | { kind: 'exhaust' }
+  | { kind: 'skip'; reason: ReconnectSkipReason };
+
+export type ReconnectSkipReason =
+  | 'not-remote'
+  | 'pane-alive'
+  | 'guarded'
+  | 'in-flight'
+  | 'not-due'
+  | 'exhausted'
+  | 'disabled';
+
+export interface DecideReconnectInput {
+  session: ReconnectSessionView;
+  state: RemoteReconnectState | undefined;
+  /** Session is in the intentional-teardown guard set (killed/detached/stopping). */
+  guarded: boolean;
+  /** Kill-switch: `remoteAutoReconnect` setting. When false, never reconnect. */
+  enabled: boolean;
+  now: number;
+}
+
+/**
+ * PURE eligibility decision for one session on one tick. No clock, no I/O — all
+ * inputs are passed in. The watcher translates the result into emits + state
+ * transitions.
+ *
+ * Order of guards (most-decisive first):
+ *  1. kill-switch off            → skip:disabled
+ *  2. not a remote session       → skip:not-remote
+ *  3. pane is alive              → skip:pane-alive
+ *  4. intentional teardown guard → skip:guarded   (NEVER revive a killed tab)
+ *  5. a reattach already running → skip:in-flight (no stacked respawns)
+ *  6. already exhausted          → skip:exhausted (one exhaust emit, then quiet)
+ *  7. cap reached this tick      → exhaust
+ *  8. not yet due (backoff)      → skip:not-due
+ *  9. otherwise                  → emit (attempt = attempts + 1)
+ */
+export function decideReconnect(input: DecideReconnectInput): ReconnectAction {
+  const { session, state, guarded, enabled, now } = input;
+
+  if (!enabled) return { kind: 'skip', reason: 'disabled' };
+  if (!session.isRemote) return { kind: 'skip', reason: 'not-remote' };
+  if (!session.paneDead) return { kind: 'skip', reason: 'pane-alive' };
+  // Intentional kill / detach must NEVER be auto-revived.
+  if (guarded) return { kind: 'skip', reason: 'guarded' };
+
+  const s = state ?? freshReconnectState();
+
+  // Only one reconnect in flight per session — don't stack respawns.
+  if (s.inFlight) return { kind: 'skip', reason: 'in-flight' };
+
+  if (s.exhausted) return { kind: 'skip', reason: 'exhausted' };
+
+  // Cap reached: surface exhaustion once, then go quiet.
+  if (isExhausted(s.attempts)) return { kind: 'exhaust' };
+
+  // Backoff gate — only emit when due.
+  if (now < s.nextEligibleAt) return { kind: 'skip', reason: 'not-due' };
+
+  return { kind: 'emit', attempt: s.attempts + 1 };
+}

src/services/unified-session-service.ts

@@ -28,9 +28,15 @@ export type UnifiedSessionItem = {
   lastActivityAt?: number;
   claudeSessionId?: string;
   firstPrompt?: string;
+  /** Most recent user prompt from the transcript (COD-145), parallel to firstPrompt. */
+  lastPrompt?: string;
   sizeBytes?: number;
   projectKey?: string;
   remote?: boolean;
+  /** Pinned to the top of the session manager list (COD-139). */
+  pinned?: boolean;
+  /** When the session was pinned (epoch ms) — orders the pinned group desc. */
+  pinnedAt?: number;
   sources: string[];
   stats?: { memoryMB: number; cpuPercent: number };
 };
@@ -46,6 +52,8 @@ export type LiveSessionInput = {
   createdAt?: number;
   lastActivityAt?: number;
   claudeSessionId?: string;
+  pinned?: boolean;
+  pinnedAt?: number;
 };
 
 /** Persisted session view (subset of `SessionState`). */
@@ -59,6 +67,8 @@ export type PersistedSessionInput = {
   lastActivityAt?: number;
   /** Claude conversation ID this session resumes (`SessionState.resumeSessionId`). */
   claudeSessionId?: string;
+  pinned?: boolean;
+  pinnedAt?: number;
 };
 
 /** Lifecycle audit-log view. Entries are expected NEWEST-first (the order `SessionLifecycleLog.query()` returns). */
@@ -77,6 +87,8 @@ export type HistoryInput = {
   sizeBytes: number;
   lastModified: string;
   firstPrompt?: string;
+  /** Most recent user prompt from the transcript (COD-145). */
+  lastPrompt?: string;
   projectKey?: string;
 };
 
@@ -149,6 +161,7 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
     overwrite(item, 'workingDir', h.workingDir);
     overwrite(item, 'sizeBytes', h.sizeBytes);
     overwrite(item, 'firstPrompt', h.firstPrompt);
+    overwrite(item, 'lastPrompt', h.lastPrompt);
     overwrite(item, 'projectKey', h.projectKey);
     const ms = Date.parse(h.lastModified);
     if (!Number.isNaN(ms) && item.lastActivityAt === undefined) item.lastActivityAt = ms;
@@ -175,6 +188,8 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
     overwrite(item, 'workingDir', p.workingDir);
     overwrite(item, 'createdAt', p.createdAt);
     overwrite(item, 'lastActivityAt', p.lastActivityAt);
+    overwrite(item, 'pinned', p.pinned);
+    overwrite(item, 'pinnedAt', p.pinnedAt);
   }
 
   // 4) live (highest precedence)
@@ -189,6 +204,8 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
     overwrite(item, 'createdAt', v.createdAt);
     overwrite(item, 'lastActivityAt', v.lastActivityAt);
     overwrite(item, 'claudeSessionId', v.claudeSessionId);
+    overwrite(item, 'pinned', v.pinned);
+    overwrite(item, 'pinnedAt', v.pinnedAt);
   }
 
   // 5) mux stats + remote flag (create item if mux-only)
@@ -200,6 +217,64 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
     if (m.remote !== undefined) item.remote = m.remote;
   }
 
+  // firstPrompt backfill (COD-140): the only source that sets firstPrompt is the
+  // transcript-history view, keyed by the Claude transcript file's UUID. A live/persisted
+  // row keyed by its Codeman id only inherits firstPrompt when that id happens to equal an
+  // on-disk transcript UUID. When it doesn't (stale/wrong claudeSessionId, post-/clear new
+  // uuid, resumed/attached/worktree session, transcript not yet flushed), the row shows
+  // "(no prompt captured)" even though a real transcript for that working dir exists under a
+  // different UUID. Backfill from the already-passed history: first try the claudeSessionId
+  // join, then the newest transcript in the same workingDir. Never overwrite a non-empty
+  // firstPrompt (so rows keyed to their own transcript are untouched).
+  const firstPromptByUuid = new Map<string, string>();
+  const firstPromptByWorkingDir = new Map<string, { prompt: string; ms: number }>();
+  // COD-145: lastPrompt rides the same backfill (build parallel indexes; never overwrite).
+  const lastPromptByUuid = new Map<string, string>();
+  const lastPromptByWorkingDir = new Map<string, { prompt: string; ms: number }>();
+  for (const h of sources.history ?? []) {
+    const ms = Date.parse(h.lastModified);
+    const ts = Number.isNaN(ms) ? -Infinity : ms;
+    if (h.firstPrompt) {
+      firstPromptByUuid.set(h.sessionId, h.firstPrompt);
+      if (h.workingDir) {
+        const existing = firstPromptByWorkingDir.get(h.workingDir);
+        if (!existing || ts > existing.ms) {
+          firstPromptByWorkingDir.set(h.workingDir, { prompt: h.firstPrompt, ms: ts });
+        }
+      }
+    }
+    if (h.lastPrompt) {
+      lastPromptByUuid.set(h.sessionId, h.lastPrompt);
+      if (h.workingDir) {
+        const existing = lastPromptByWorkingDir.get(h.workingDir);
+        if (!existing || ts > existing.ms) {
+          lastPromptByWorkingDir.set(h.workingDir, { prompt: h.lastPrompt, ms: ts });
+        }
+      }
+    }
+  }
+  for (const item of map.values()) {
+    if (!item.firstPrompt) {
+      // never overwrite an existing non-empty prompt
+      const byUuid = item.claudeSessionId ? firstPromptByUuid.get(item.claudeSessionId) : undefined;
+      if (byUuid) {
+        item.firstPrompt = byUuid;
+      } else if (item.workingDir) {
+        const byDir = firstPromptByWorkingDir.get(item.workingDir);
+        if (byDir) item.firstPrompt = byDir.prompt;
+      }
+    }
+    if (!item.lastPrompt) {
+      const byUuid = item.claudeSessionId ? lastPromptByUuid.get(item.claudeSessionId) : undefined;
+      if (byUuid) {
+        item.lastPrompt = byUuid;
+      } else if (item.workingDir) {
+        const byDir = lastPromptByWorkingDir.get(item.workingDir);
+        if (byDir) item.lastPrompt = byDir.prompt;
+      }
+    }
+  }
+
   // Meaningfulness floor: keep real rows, drop bare lifecycle/mux-only noise.
   const kept: UnifiedSessionItem[] = [];
   for (const item of map.values()) {
@@ -211,8 +286,24 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
     if (isReal) kept.push(item);
   }
 
-  // Stable sort: lastActivityAt desc (undefined last), createdAt desc, sessionId asc.
+  // Stable sort (COD-139): pinned group first (pinnedAt desc, most-recently-pinned
+  // first), then unpinned by lastActivityAt desc (undefined last), createdAt desc,
+  // sessionId asc.
   kept.sort((a, b) => {
+    const pa = a.pinned === true;
+    const pb = b.pinned === true;
+    if (pa !== pb) return pa ? -1 : 1; // pinned floats above unpinned
+    if (pa && pb) {
+      // Both pinned: most-recently-pinned first (undefined pinnedAt sorts last).
+      const ta = a.pinnedAt;
+      const tb = b.pinnedAt;
+      if (ta !== tb) {
+        if (ta === undefined) return 1;
+        if (tb === undefined) return -1;
+        return tb - ta;
+      }
+      // tie-break falls through to the activity/createdAt/id rules below.
+    }
     const la = a.lastActivityAt;
     const lb = b.lastActivityAt;
     if (la !== lb) {
@@ -234,7 +325,7 @@ export function mergeUnifiedSessions(sources: UnifiedSources): UnifiedSessionIte
 }
 
 /**
- * Case-insensitive substring filter (name + firstPrompt + workingDir + sessionId)
+ * Case-insensitive substring filter (name + firstPrompt + lastPrompt + workingDir + sessionId)
  * with offset/limit paging. `total` is the filtered count BEFORE paging.
  */
 export function filterAndPaginate(
@@ -244,7 +335,7 @@ export function filterAndPaginate(
   const q = (opts.q ?? '').trim().toLowerCase();
   const filtered = q
     ? items.filter((it) => {
-        const hay = [it.name, it.firstPrompt, it.workingDir, it.sessionId]
+        const hay = [it.name, it.firstPrompt, it.lastPrompt, it.workingDir, it.sessionId]
           .filter((v): v is string => typeof v === 'string')
           .join(' ')
           .toLowerCase();

src/session-cli-builder.ts

@@ -21,6 +21,8 @@ function buildPermissionArgs(claudeMode: ClaudeMode, allowedTools?: string): str
   switch (claudeMode) {
     case 'dangerously-skip-permissions':
       return ['--dangerously-skip-permissions'];
+    case 'auto':
+      return ['--permission-mode', 'auto'];
     case 'allowedTools':
       if (allowedTools) {
         return ['--allowedTools', allowedTools];
@@ -80,8 +82,16 @@ export function buildInteractiveArgs(
  * @param model - Optional model override
  * @returns Array of CLI arguments
  */
-export function buildPromptArgs(prompt: string, model?: string): string[] {
-  const args = ['-p', '--verbose', '--dangerously-skip-permissions', '--output-format', 'stream-json'];
+export function buildPromptArgs(
+  prompt: string,
+  model?: string,
+  claudeMode: ClaudeMode = 'dangerously-skip-permissions',
+  allowedTools?: string
+): string[] {
+  // Respect the session's permission mode instead of always skipping, so a
+  // multi-user non-granted user's one-shot runs classifier-guarded (auto) rather
+  // than with full bypass. Defaults to skip-permissions (unchanged single-user).
+  const args = ['-p', '--verbose', ...buildPermissionArgs(claudeMode, allowedTools), '--output-format', 'stream-json'];
   if (model) {
     args.push('--model', model);
   }

src/session-order.ts

@@ -0,0 +1,68 @@
+/**
+ * @fileoverview Pure helpers for the global session tab-order (COD-131).
+ *
+ * Tab order (drag-and-drop reorder + Ctrl+Shift+{/}) is persisted server-side
+ * so it follows the user across devices. The server is authoritative; the
+ * browser's localStorage (`codeman-session-order`) is the offline fallback.
+ *
+ * These helpers are pure (no IO) so they can be unit-tested in isolation and
+ * reused by both the PUT /api/session-order route and the StateStore accessor.
+ *
+ * - `normalizeSessionOrder` coerces arbitrary input into a clean string[]
+ *   (non-empty strings only, deduped with first occurrence winning).
+ * - `mergeSessionOrder` lets the pushing device's order win, while preserving
+ *   any server-only ids the pushing device didn't know about — they fall to the
+ *   END in their existing relative order, never dropped.
+ */
+
+/**
+ * Coerce arbitrary input into a clean ordered list of session ids:
+ * keep only non-empty strings and dedup (first occurrence wins).
+ *
+ * @param order - unknown input (expected to be a string[], but defensive)
+ * @returns a normalized string[] (empty array for non-array / all-junk input)
+ */
+export function normalizeSessionOrder(order: unknown): string[] {
+  if (!Array.isArray(order)) {
+    return [];
+  }
+  const seen = new Set<string>();
+  const result: string[] = [];
+  for (const entry of order) {
+    if (typeof entry !== 'string' || entry.length === 0) {
+      continue;
+    }
+    if (seen.has(entry)) {
+      continue;
+    }
+    seen.add(entry);
+    result.push(entry);
+  }
+  return result;
+}
+
+/**
+ * Merge an incoming order from a pushing device with the existing server order.
+ *
+ * The incoming order wins; any ids present in `existing` but NOT in `incoming`
+ * are appended at the END, preserving their relative order. This is the
+ * "server-only ids the pushing device didn't know about fall to the end, never
+ * dropped" rule.
+ *
+ * Both arguments are normalized first, so callers may pass raw input safely.
+ *
+ * @param incoming - the order the pushing device wants
+ * @param existing - the current server-side order
+ * @returns the merged, normalized order
+ */
+export function mergeSessionOrder(incoming: string[], existing: string[]): string[] {
+  const normalizedIncoming = normalizeSessionOrder(incoming);
+  const incomingSet = new Set(normalizedIncoming);
+  const merged = [...normalizedIncoming];
+  for (const id of normalizeSessionOrder(existing)) {
+    if (!incomingSet.has(id)) {
+      merged.push(id);
+    }
+  }
+  return merged;
+}

src/session.ts

@@ -49,6 +49,7 @@ import {
   type CodexConfig,
   type EffortLevel,
   type GeminiConfig,
+  type AntigravityConfig,
   type SessionRemote,
   type SessionDocker,
 } from './types.js';
@@ -65,6 +66,9 @@ import {
   MAX_SESSION_TOKENS,
   execPattern,
   getClaudeCliVersion,
+  getClaudeBinaryPath,
+  spawnPtyWithHelperRepair,
+  resolveLocalShell,
 } from './utils/index.js';
 import {
   MAX_TERMINAL_BUFFER_SIZE,
@@ -140,7 +144,7 @@ const NEWLINE_SPLIT_PATTERN = /\r?\n/;
 
 /** True for external-CLI run modes (non-Claude) that use their own TUI and output format. */
 export function isExternalCliMode(mode: SessionMode): boolean {
-  return mode === 'opencode' || mode === 'codex' || mode === 'gemini';
+  return mode === 'opencode' || mode === 'codex' || mode === 'gemini' || mode === 'antigravity';
 }
 
 function getModeLabel(mode: SessionMode): string {
@@ -151,6 +155,8 @@ function getModeLabel(mode: SessionMode): string {
       return 'Codex';
     case 'gemini':
       return 'Gemini';
+    case 'antigravity':
+      return 'Antigravity';
     case 'shell':
       return 'Shell';
     case 'claude':
@@ -180,6 +186,13 @@ export function isAltScreenStripMode(mode: SessionMode): boolean {
 const DEFAULT_PTY_COLS = 120;
 const DEFAULT_PTY_ROWS = 40;
 const TMUX_DISPLAY_TIMEOUT_MS = 2000;
+const IS_TEST_MODE = !!process.env.VITEST;
+/**
+ * Echo transport for the test-mode PTY attach. Raw mode disables the tty line
+ * discipline, so each input byte flows back exactly once and immediately; without
+ * it, tty echo doubles every line and canonical buffering holds bytes until Enter.
+ */
+const TEST_PTY_SCRIPT = 'if (process.stdin.isTTY) process.stdin.setRawMode(true); process.stdin.pipe(process.stdout);';
 /** Delay before the in-container Claude CLI version probe (lets the container start). */
 const DOCKER_CLI_VERSION_PROBE_DELAY_MS = 3000;
 
@@ -342,6 +355,11 @@ export class Session extends EventEmitter {
   // Image watcher setting (per-session toggle)
   private _imageWatcherEnabled: boolean = false;
 
+  // Pin state (COD-139) — pinned sessions float to the top of the session
+  // manager list, ordered by pinnedAt descending (most-recently-pinned first).
+  private _pinned: boolean = false;
+  private _pinnedAt: number | null = null;
+
   // Flicker filter setting (per-session toggle, applied on frontend)
   private _flickerFilterEnabled: boolean = false;
 
@@ -391,6 +409,8 @@ export class Session extends EventEmitter {
   private _codexConfig: CodexConfig | undefined;
   // Gemini configuration (only for mode === 'gemini')
   private _geminiConfig: GeminiConfig | undefined;
+  // Antigravity configuration (only for mode === 'antigravity')
+  private _antigravityConfig: AntigravityConfig | undefined;
   private _resumeSessionId: string | undefined;
 
   // Ephemeral env overrides (e.g., CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS). Exported by tmux
@@ -412,6 +432,10 @@ export class Session extends EventEmitter {
   // local tmux + `docker exec`. The container is per-CASE (shared by sibling sessions).
   private readonly _docker?: SessionDocker;
 
+  // Owning username in multi-user mode (undefined in single-user). Stamped at create
+  // from req.authUser and round-tripped through recovery like _remote/_docker.
+  private _owner?: string;
+
   // Session color for visual differentiation
   private _color: import('./types.js').SessionColor = 'default';
 
@@ -473,6 +497,8 @@ export class Session extends EventEmitter {
       codexConfig?: CodexConfig;
       /** Gemini configuration (only for mode === 'gemini') */
       geminiConfig?: GeminiConfig;
+      /** Antigravity configuration (only for mode === 'antigravity') */
+      antigravityConfig?: AntigravityConfig;
       /** Resume a previous Claude conversation (used after server reboot) */
       resumeSessionId?: string;
       /** Extra env vars exported to the CLI at spawn time (no disk persistence) */
@@ -487,6 +513,8 @@ export class Session extends EventEmitter {
       remote?: SessionRemote;
       /** Docker execution metadata for sessions launched inside a container via local tmux. */
       docker?: SessionDocker;
+      /** Owning username (multi-user mode); undefined in single-user. */
+      owner?: string;
     }
   ) {
     super();
@@ -544,6 +572,11 @@ export class Session extends EventEmitter {
       this._geminiConfig = config.geminiConfig;
     }
 
+    // Apply Antigravity configuration
+    if (config.antigravityConfig) {
+      this._antigravityConfig = config.antigravityConfig;
+    }
+
     // Apply env overrides (exported at spawn, not persisted to disk).
     // Legacy migration: pre-0.7.2 carried effort as the CLAUDE_CODE_EFFORT_LEVEL env var,
     // which hard-locks /effort switching. Extract it into _effort (--settings soft default)
@@ -561,6 +594,7 @@ export class Session extends EventEmitter {
     this._tmuxHistoryLimit = config.tmuxHistoryLimit ?? DEFAULT_TMUX_HISTORY_LIMIT;
     this._remote = config.remote;
     this._docker = config.docker;
+    this._owner = config.owner;
     if (config.attachmentHistory && config.attachmentHistory.length > 0) {
       this.restoreAttachmentHistory(config.attachmentHistory);
     }
@@ -667,6 +701,16 @@ export class Session extends EventEmitter {
     return this._docker;
   }
 
+  /** Owning username in multi-user mode, else undefined. */
+  get owner(): string | undefined {
+    return this._owner;
+  }
+
+  /** Set the owning username (used by recovery to restore ownership). */
+  set owner(username: string | undefined) {
+    this._owner = username;
+  }
+
   // Adopt a Claude conversation ID observed from an external source (e.g. hook
   // payload). In interactive PTY mode Claude CLI emits no JSON to stdout, so
   // `_handleJsonMessage` never sees `session_id`; hooks are the only signal
@@ -975,6 +1019,26 @@ export class Session extends EventEmitter {
     this._imageWatcherEnabled = enabled;
   }
 
+  /** Whether this session is pinned to the top of the session manager (COD-139). */
+  get pinned(): boolean {
+    return this._pinned;
+  }
+
+  /** When the session was pinned (epoch ms), or null when unpinned. */
+  get pinnedAt(): number | null {
+    return this._pinnedAt;
+  }
+
+  /**
+   * Set pin state (COD-139). Pinning stamps pinnedAt with now so the pinned
+   * group orders most-recently-pinned first; unpinning clears it. Idempotent:
+   * re-pinning an already-pinned session refreshes its pinnedAt.
+   */
+  setPinned(pinned: boolean): void {
+    this._pinned = pinned;
+    this._pinnedAt = pinned ? Date.now() : null;
+  }
+
   get flickerFilterEnabled(): boolean {
     return this._flickerFilterEnabled;
   }
@@ -1027,6 +1091,7 @@ export class Session extends EventEmitter {
       workingDir: this.workingDir,
       remote: this._remote,
       docker: this._docker,
+      owner: this._owner,
       currentTaskId: this._currentTaskId,
       createdAt: this.createdAt,
       lastActivityAt: this._lastActivityAt,
@@ -1040,6 +1105,8 @@ export class Session extends EventEmitter {
       autoResumeEnabled: this._autoOps.autoResumeEnabled,
       autoResumeAt: this._autoOps.autoResumeAt ?? undefined,
       imageWatcherEnabled: this._imageWatcherEnabled,
+      pinned: this._pinned || undefined,
+      pinnedAt: this._pinned ? (this._pinnedAt ?? undefined) : undefined,
       totalCost: this._totalCost,
       inputTokens: this._totalInputTokens,
       outputTokens: this._totalOutputTokens,
@@ -1059,6 +1126,7 @@ export class Session extends EventEmitter {
       openCodeConfig: this._openCodeConfig,
       codexConfig: this._codexConfig,
       geminiConfig: this._geminiConfig,
+      antigravityConfig: this._antigravityConfig,
       resumeSessionId: this._resumeSessionId,
       effort: this._effort,
       // COD-118: runtime-only — surfaced so the frontend can require explicit user
@@ -1203,24 +1271,33 @@ export class Session extends EventEmitter {
       // No extra sleep — createSession() already waits for tmux readiness
     }
 
-    // Attach to the mux session via PTY
-    // Prevent tmux from letting the newest browser attach dictate global window
-    // size; accepted Codeman resize events update it explicitly below.
-    mux.setManualWindowSize?.(this._muxSession!.muxName);
+    // Integration tests need a live input/output transport without attaching to
+    // the host's tmux server or agent CLI. Production still uses the real mux.
+    if (!IS_TEST_MODE) {
+      // Prevent tmux from letting the newest browser attach dictate global window
+      // size; accepted Codeman resize events update it explicitly below.
+      mux.setManualWindowSize?.(this._muxSession!.muxName);
+    }
     // Query existing tmux window size so re-attach matches (avoids flicker from 120x40 default).
     // MUST go through the dedicated socket (mux.muxSocket); a bare `tmux display` hits the
     // default server, always fails for our socketed sessions, and silently falls back to 120x40.
-    const { cols: ptyCols, rows: ptyRows } = queryTmuxWindowSize(this._muxSession!.muxName, mux.muxSocket);
+    const { cols: ptyCols, rows: ptyRows } = IS_TEST_MODE
+      ? { cols: DEFAULT_PTY_COLS, rows: DEFAULT_PTY_ROWS }
+      : queryTmuxWindowSize(this._muxSession!.muxName, mux.muxSocket);
+    const attachCommand = IS_TEST_MODE ? process.execPath : mux.getAttachCommand();
+    const attachArgs = IS_TEST_MODE ? ['-e', TEST_PTY_SCRIPT] : mux.getAttachArgs(this._muxSession!.muxName);
     try {
-      this.ptyProcess = pty.spawn(mux.getAttachCommand(), mux.getAttachArgs(this._muxSession!.muxName), {
-        name: 'xterm-256color',
-        cols: ptyCols,
-        rows: ptyRows,
-        cwd: resolveMuxAttachCwd(this.workingDir, this._remote, this._docker),
-        // COD-75: codex/gemini get COLORTERM=truecolor — mirrors buildEnvExports()
-        // in tmux-manager.ts so the attach client and the tmux session agree.
-        env: buildMuxAttachEnv(this.mode === 'codex' || this.mode === 'gemini'),
-      });
+      this.ptyProcess = spawnPtyWithHelperRepair(() =>
+        pty.spawn(attachCommand, attachArgs, {
+          name: 'xterm-256color',
+          cols: ptyCols,
+          rows: ptyRows,
+          cwd: resolveMuxAttachCwd(this.workingDir, this._remote, this._docker),
+          // COD-75: codex/gemini/antigravity get COLORTERM=truecolor — mirrors buildEnvExports()
+          // in tmux-manager.ts so the attach client and the tmux session agree.
+          env: buildMuxAttachEnv(this.mode === 'codex' || this.mode === 'gemini' || this.mode === 'antigravity'),
+        })
+      );
     } catch (spawnErr) {
       console.error(`[Session] Failed to spawn PTY for ${options.spawnErrLabel}:`, spawnErr);
       this.emit('error', `Failed to attach to mux session: ${spawnErr}`);
@@ -1230,6 +1307,71 @@ export class Session extends EventEmitter {
     return { isRestored };
   }
 
+  /**
+   * COD-108 — re-establish a dropped REMOTE session. Triggered by the
+   * `TmuxManager` remote-reconnect watcher (via `remoteSessionDropped`): the
+   * watcher detects a dead remote pane, the session owner reassembles the SAME
+   * `RespawnPaneOptions` used for Claude-idle respawns and calls
+   * `respawnPane()` directly. For a remote session that re-runs
+   * `buildRemoteSessionCommand` (owned → `new-session -A`, non-owned →
+   * `attach`), which idempotently REATTACHES the still-running durable remote
+   * tmux session — scrollback + agent intact (proven COD-104/105).
+   *
+   * Deliberately does NOT route through the Claude-idle respawn-controller —
+   * this is a transport re-establish, not a `/clear`/`/compact` cycle.
+   *
+   * @returns true if the pane was respawned (reattach issued), false otherwise.
+   */
+  async reattachRemote(): Promise<boolean> {
+    if (!this._remote) return false; // not a remote session
+    if (!this._useMux || !this._mux || !this._muxSession) return false;
+    const mux = this._mux;
+
+    // If tmux lost the whole session (not just a dead pane), there is nothing to
+    // respawn into — a genuine death, leave it for normal recovery/reconcile.
+    if (!mux.muxSessionExists(this._muxSession.muxName)) {
+      console.log('[Session] reattachRemote: mux session gone, skipping:', this._muxSession.muxName);
+      return false;
+    }
+
+    const newPid = await mux.respawnPane(this._buildRespawnPaneOptions());
+    if (!newPid) {
+      console.error('[Session] reattachRemote: respawnPane failed for', this._muxSession.muxName);
+      return false;
+    }
+    console.log('[Session] reattachRemote: reattached remote session', this._muxSession.muxName, 'pid', newPid);
+    return true;
+  }
+
+  /**
+   * Assemble the {@link RespawnPaneOptions} for this session. Single source of
+   * truth shared by interactive start, shell start (via their inline copies),
+   * and {@link reattachRemote} so the remote reattach path can never drift from
+   * the spawn path.
+   */
+  private _buildRespawnPaneOptions(): import('./mux-interface.js').RespawnPaneOptions {
+    return {
+      sessionId: this.id,
+      workingDir: this.workingDir,
+      mode: this.mode,
+      niceConfig: this._niceConfig,
+      model: this._model,
+      claudeMode: this._claudeMode,
+      allowedTools: this._allowedTools,
+      openCodeConfig: this._openCodeConfig,
+      codexConfig: this._codexConfig,
+      geminiConfig: this._geminiConfig,
+      antigravityConfig: this._antigravityConfig,
+      resumeSessionId: this._resumeSessionId,
+      envOverrides: this._envOverrides,
+      effort: this._effort,
+      historyLimit: this._tmuxHistoryLimit,
+      remote: this._remote,
+      docker: this._docker,
+      owner: this._owner,
+    };
+  }
+
   private _handleTerminalOutput(data: string): void {
     // Codex AND Claude Code emit sequences that wipe xterm.js scrollback, plus
     // mouse-tracking enables that hijack the scroll wheel so the user can't reach
@@ -1378,24 +1520,8 @@ export class Session extends EventEmitter {
     if (this._useMux && this._mux) {
       try {
         const { isRestored } = await this._setupOrAttachMuxSession({
-          respawnPaneOptions: {
-            sessionId: this.id,
-            workingDir: this.workingDir,
-            mode: this.mode,
-            niceConfig: this._niceConfig,
-            model: this._model,
-            claudeMode: this._claudeMode,
-            allowedTools: this._allowedTools,
-            openCodeConfig: this._openCodeConfig,
-            codexConfig: this._codexConfig,
-            geminiConfig: this._geminiConfig,
-            resumeSessionId: this._resumeSessionId,
-            envOverrides: this._envOverrides,
-            effort: this._effort,
-            historyLimit: this._tmuxHistoryLimit,
-            remote: this._remote,
-            docker: this._docker,
-          },
+          // Single source of truth shared with reattachRemote() (COD-108).
+          respawnPaneOptions: this._buildRespawnPaneOptions(),
           createSessionOptions: {
             sessionId: this.id,
             workingDir: this.workingDir,
@@ -1408,12 +1534,14 @@ export class Session extends EventEmitter {
             openCodeConfig: this._openCodeConfig,
             codexConfig: this._codexConfig,
             geminiConfig: this._geminiConfig,
+            antigravityConfig: this._antigravityConfig,
             resumeSessionId: this._resumeSessionId,
             envOverrides: this._envOverrides,
             effort: this._effort,
             historyLimit: this._tmuxHistoryLimit,
             remote: this._remote,
             docker: this._docker,
+            owner: this._owner,
           },
           spawnErrLabel: 'mux attachment',
         });
@@ -1488,18 +1616,24 @@ export class Session extends EventEmitter {
       if (this.mode === 'gemini') {
         throw new Error('Gemini sessions require tmux. Direct PTY fallback is not supported.');
       }
+      // Antigravity sessions require tmux for env override injection via setenv
+      if (this.mode === 'antigravity') {
+        throw new Error('Antigravity sessions require tmux. Direct PTY fallback is not supported.');
+      }
       try {
         // Pass --session-id to use the SAME ID as the Codeman session
         // This ensures subagents can be directly matched to the correct tab
         const args = buildInteractiveArgs(this.id, this._claudeMode, this._model, this._allowedTools, this._effort);
-        this.ptyProcess = pty.spawn('claude', args, {
-          name: 'xterm-256color',
-          cols: 120,
-          rows: 40,
-          cwd: this.workingDir,
-          // Merge envOverrides after buildClaudeEnv so user settings shadow defaults.
-          env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
-        });
+        this.ptyProcess = spawnPtyWithHelperRepair(() =>
+          pty.spawn(getClaudeBinaryPath(), args, {
+            name: 'xterm-256color',
+            cols: 120,
+            rows: 40,
+            cwd: this.workingDir,
+            // Merge envOverrides after buildClaudeEnv so user settings shadow defaults.
+            env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
+          })
+        );
       } catch (spawnErr) {
         console.error('[Session] Failed to spawn Claude PTY:', spawnErr);
         this._status = 'stopped';
@@ -1523,7 +1657,7 @@ export class Session extends EventEmitter {
 
       // === Auto-accept workspace trust dialog ===
       // Claude CLI 2.x shows "Yes, I trust this folder" prompt on first launch per directory.
-      // Codeman sessions always use --dangerously-skip-permissions, so auto-accept.
+      // Codeman sessions run permission-skipping or classifier-guarded (auto) modes, so auto-accept.
       if (!this._trustDialogAccepted && data.includes('trust this folder')) {
         this._trustDialogAccepted = true;
         console.log(`[Session] Auto-accepting workspace trust dialog for: ${this.id}`);
@@ -1765,8 +1899,9 @@ export class Session extends EventEmitter {
 
     this._resetBuffers();
 
-    // Use user's default shell or bash
-    const shell = process.env.SHELL || '/bin/bash';
+    // Use user's default shell, falling back to a shell that actually exists.
+    // Shared with the tmux pane command so both paths launch the same binary.
+    const shell = resolveLocalShell();
     console.log(
       '[Session] Starting shell session with:',
       shell + (this._useMux ? ` (with ${this._mux!.backend})` : '')
@@ -1785,6 +1920,7 @@ export class Session extends EventEmitter {
             historyLimit: this._tmuxHistoryLimit,
             remote: this._remote,
             docker: this._docker,
+            owner: this._owner,
           },
           createSessionOptions: {
             sessionId: this.id,
@@ -1796,6 +1932,7 @@ export class Session extends EventEmitter {
             historyLimit: this._tmuxHistoryLimit,
             remote: this._remote,
             docker: this._docker,
+            owner: this._owner,
           },
           spawnErrLabel: 'shell mux attachment',
         });
@@ -1820,13 +1957,15 @@ export class Session extends EventEmitter {
     // Fallback to direct PTY if mux is not used
     if (!this.ptyProcess) {
       try {
-        this.ptyProcess = pty.spawn(shell, [], {
-          name: 'xterm-256color',
-          cols: 120,
-          rows: 40,
-          cwd: this.workingDir,
-          env: buildShellEnv(this.id),
-        });
+        this.ptyProcess = spawnPtyWithHelperRepair(() =>
+          pty.spawn(shell, [], {
+            name: 'xterm-256color',
+            cols: 120,
+            rows: 40,
+            cwd: this.workingDir,
+            env: buildShellEnv(this.id),
+          })
+        );
       } catch (spawnErr) {
         console.error('[Session] Failed to spawn shell PTY:', spawnErr);
         this._status = 'stopped';
@@ -1923,17 +2062,19 @@ export class Session extends EventEmitter {
           model ? `(model: ${model})` : ''
         );
 
-        const args = buildPromptArgs(prompt, model);
+        const args = buildPromptArgs(prompt, model, this._claudeMode, this._allowedTools);
 
         try {
-          this.ptyProcess = pty.spawn('claude', args, {
-            name: 'xterm-256color',
-            cols: 120,
-            rows: 40,
-            cwd: this.workingDir,
-            // Merge envOverrides after buildClaudeEnv so user settings shadow defaults.
-            env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
-          });
+          this.ptyProcess = spawnPtyWithHelperRepair(() =>
+            pty.spawn(getClaudeBinaryPath(), args, {
+              name: 'xterm-256color',
+              cols: 120,
+              rows: 40,
+              cwd: this.workingDir,
+              // Merge envOverrides after buildClaudeEnv so user settings shadow defaults.
+              env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
+            })
+          );
         } catch (spawnErr) {
           console.error('[Session] Failed to spawn Claude PTY for runPrompt:', spawnErr);
           this.emit(
@@ -2587,7 +2728,7 @@ export class Session extends EventEmitter {
     if (this.ptyProcess && (dimsChanged || options.force)) {
       this._ptyCols = cols;
       this._ptyRows = rows;
-      if (this._mux && this._muxSession) {
+      if (!IS_TEST_MODE && this._mux && this._muxSession) {
         this._mux.resizeWindow?.(this._muxSession.muxName, cols, rows);
       }
       this.ptyProcess.resize(cols, rows);

src/state-store.ts

@@ -278,6 +278,9 @@ export class StateStore {
     if (this.state.cronJobRuns) {
       parts.push(`"cronJobRuns":${JSON.stringify(this.state.cronJobRuns)}`);
     }
+    if (this.state.sessionOrder) {
+      parts.push(`"sessionOrder":${JSON.stringify(this.state.sessionOrder)}`);
+    }
 
     return `{${parts.join(',')}}`;
   }
@@ -485,6 +488,25 @@ export class StateStore {
     this.save();
   }
 
+  /**
+   * COD-142: Remove a session's persisted record on kill UNLESS it is pinned.
+   * A pinned session is demoted to a lightweight `stopped` record (pin retained)
+   * so it stays visible in the session-manager pinned group and survives restart.
+   * Unpinned sessions are fully removed (unchanged behavior).
+   * @returns 'preserved' if demoted to stopped+pinned, 'removed' if deleted, 'absent' if no record existed.
+   */
+  demoteOrRemoveSession(id: string): 'preserved' | 'removed' | 'absent' {
+    const existing = this.state.sessions[id];
+    if (!existing) return 'absent';
+    if (existing.pinned === true) {
+      // Demote in place: keep identity/resume fields + pin, mark stopped, clear live runtime.
+      this.setSession(id, { ...existing, status: 'stopped', pid: null });
+      return 'preserved';
+    }
+    this.removeSession(id);
+    return 'removed';
+  }
+
   /**
    * Cleans up stale sessions from state that don't have corresponding active sessions.
    * @param activeSessionIds - Set of currently active session IDs
@@ -499,6 +521,7 @@ export class StateStore {
 
     for (const sessionId of allSessionIds) {
       if (!activeSessionIds.has(sessionId)) {
+        if (this.state.sessions[sessionId]?.pinned === true) continue; // COD-142: pinned records persist even with no live session
         const name = this.state.sessions[sessionId]?.name;
         cleaned.push({ id: sessionId, name });
         delete this.state.sessions[sessionId];
@@ -630,6 +653,17 @@ export class StateStore {
     this.save();
   }
 
+  /** Returns the global tab order (ordered sessionIds), [] if unset. COD-131. */
+  getSessionOrder(): string[] {
+    return this.state.sessionOrder ?? [];
+  }
+
+  /** Persists the global tab order (ordered sessionIds) and triggers a debounced save. COD-131. */
+  setSessionOrder(order: string[]): void {
+    this.state.sessionOrder = order;
+    this.save();
+  }
+
   /** Resets all state to initial values and saves immediately. */
   reset(): void {
     this.state = createInitialState();

src/tmux-manager.ts

@@ -43,12 +43,18 @@ import {
   type CodexConfig,
   type EffortLevel,
   type GeminiConfig,
+  type AntigravityConfig,
   type SessionRemote,
   type SessionDocker,
   type DockerCommandMode,
 } from './types.js';
 import { buildEffortCliArgs } from './session-cli-builder.js';
-import { buildSshConnectionArgs, defaultRemoteCommandForMode, remoteSshTarget } from './remote-hosts.js';
+import {
+  buildSshConnectionArgs,
+  defaultRemoteCommandForMode,
+  remoteLoginShellCommand,
+  remoteSshTarget,
+} from './remote-hosts.js';
 import {
   buildDockerBaseArgs,
   buildDockerCreateArgs,
@@ -56,9 +62,11 @@ import {
   CONTAINER_HOME,
   defaultDockerCommandForMode,
   hostGatewayAlias,
-  resolveCredentialMounts,
+  resolveDockerClaudeArtifacts,
+  resolveDockerCredentialArtifacts,
   type DockerCreateContext,
   type DockerMount,
+  type DockerSeedCopy,
 } from './docker-hosts.js';
 import {
   wrapWithNice,
@@ -67,6 +75,9 @@ import {
   resolveOpenCodeDir,
   resolveCodexDir,
   resolveGeminiDir,
+  resolveAntigravityDir,
+  resolveLocalShell,
+  loginShellArgs,
 } from './utils/index.js';
 import type {
   TerminalMultiplexer,
@@ -76,6 +87,13 @@ import type {
   RespawnPaneOptions,
   PaneCaptureOptions,
 } from './mux-interface.js';
+import {
+  decideReconnect,
+  advanceBackoff,
+  freshReconnectState,
+  resetReconnectState,
+  type RemoteReconnectState,
+} from './remote-reconnect.js';
 
 // ============================================================================
 // Timing Constants
@@ -108,6 +126,9 @@ const GRACEFUL_SHUTDOWN_WAIT_MS = 100;
 /** Default stats collection interval (2 seconds) */
 const DEFAULT_STATS_INTERVAL_MS = 2000;
 
+/** Default remote-reconnect watcher poll interval (5 seconds) — COD-108 */
+const DEFAULT_REMOTE_RECONNECT_INTERVAL_MS = 5000;
+
 /** Stable cwd for tmux server/pane launch; actual session cwd is reached inside the pane. */
 const TMUX_LAUNCH_CWD = '/tmp';
 
@@ -132,6 +153,20 @@ const IS_TEST_MODE = !!process.env.VITEST;
 /** Path to persisted mux session metadata */
 const MUX_SESSIONS_FILE = dataPath('mux-sessions.json');
 
+/**
+ * COD-108 kill-switch: `remoteAutoReconnect` app setting (default ON). Read at
+ * call time (like headroom routing) so a settings change takes effect without a
+ * restart. Absent/non-boolean ⇒ true (feature on).
+ */
+function isRemoteAutoReconnectEnabled(): boolean {
+  try {
+    const s = JSON.parse(readFileSync(dataPath('settings.json'), 'utf8')) as Record<string, unknown>;
+    return typeof s.remoteAutoReconnect === 'boolean' ? s.remoteAutoReconnect : true;
+  } catch {
+    return true;
+  }
+}
+
 /** Regex to validate tmux session names (only allow safe characters) */
 const SAFE_MUX_NAME_PATTERN = /^codeman-[a-f0-9-]+$/;
 
@@ -561,6 +596,8 @@ function buildClaudePermissionFlags(claudeMode?: ClaudeMode, allowedTools?: stri
   switch (mode) {
     case 'dangerously-skip-permissions':
       return ' --dangerously-skip-permissions';
+    case 'auto':
+      return ' --permission-mode auto';
     case 'allowedTools':
       if (allowedTools) {
         // Sanitize: allow tool names with patterns like Bash(git:*), space/comma-separated
@@ -612,6 +649,10 @@ export function buildCodexCommand(config?: CodexConfig): string {
     parts.push('--dangerously-bypass-approvals-and-sandbox');
   }
 
+  if (config?.animations !== undefined) {
+    parts.push('--config', `tui.animations=${config.animations ? 'true' : 'false'}`);
+  }
+
   if (config?.model) {
     const safeModel = /^[a-zA-Z0-9._\-/]+$/.test(config.model) ? config.model : undefined;
     if (safeModel) parts.push('--model', safeModel);
@@ -654,6 +695,34 @@ function buildGeminiCommand(config?: GeminiConfig): string {
   return parts.join(' ');
 }
 
+/**
+ * Build the Antigravity CLI (agy) command with appropriate flags.
+ *
+ * Unlike gemini's yolo default, `--dangerously-skip-permissions` is only added
+ * when the config explicitly asks for it (the frontend sends it for parity with
+ * Codeman's Claude default; the multi-user clamp strips it for non-granted owners,
+ * and an ABSENT config stays at agy's own prompting default — safe like Codex).
+ */
+function buildAntigravityCommand(config?: AntigravityConfig): string {
+  const parts = ['agy'];
+
+  if (config?.dangerouslySkipPermissions) {
+    parts.push('--dangerously-skip-permissions');
+  }
+
+  if (config?.model) {
+    const safeModel = /^[a-zA-Z0-9._\-/]+$/.test(config.model) ? config.model : undefined;
+    if (safeModel) parts.push('--model', safeModel);
+  }
+
+  if (config?.resumeConversationId) {
+    const safeId = /^[a-zA-Z0-9._-]+$/.test(config.resumeConversationId) ? config.resumeConversationId : undefined;
+    if (safeId) parts.push('--conversation', safeId);
+  }
+
+  return parts.join(' ');
+}
+
 /**
  * Build the spawn command for any session mode.
  * Shared by createSession() and respawnPane() to avoid duplication.
@@ -672,7 +741,7 @@ function buildEffortSettingsFlag(effort?: EffortLevel): string {
   return flag && value ? ` ${flag} '${value}'` : '';
 }
 
-function buildSpawnCommand(options: {
+export function buildSpawnCommand(options: {
   mode: SessionMode;
   sessionId: string;
   model?: string;
@@ -681,6 +750,7 @@ function buildSpawnCommand(options: {
   openCodeConfig?: OpenCodeConfig;
   codexConfig?: CodexConfig;
   geminiConfig?: GeminiConfig;
+  antigravityConfig?: AntigravityConfig;
   resumeSessionId?: string;
   effort?: EffortLevel;
 }): string {
@@ -711,7 +781,24 @@ function buildSpawnCommand(options: {
   if (options.mode === 'gemini') {
     return buildGeminiCommand(options.geminiConfig);
   }
-  return '$SHELL';
+  if (options.mode === 'antigravity') {
+    return buildAntigravityCommand(options.antigravityConfig);
+  }
+  // #208: NOT the literal '$SHELL'. This string is embedded in the `bash -c "…"`
+  // argument of the respawn-pane line, which execSync runs through `/bin/sh -c`,
+  // so a `$SHELL` here is expanded by the SERVER process's shell against the
+  // SERVER process's env — empty in containers and system systemd units, leaving
+  // the pane command ending in a dangling `&&` ("syntax error: unexpected end of
+  // file", pane dead on arrival). Resolve it in Node and quote the result.
+  // #209: launch it as a LOGIN shell, which is what tmux itself does for a pane
+  // with no `default-command`, so a Codeman shell tab matches a hand-started tmux
+  // one. That is what picks up /etc/profile and /etc/profile.d/* — a systemd
+  // --user service never sourced them, so its PATH is what every pane inherited.
+  // The flags come from loginShellArgs() rather than being hardcoded: they are
+  // appended to a path that ultimately comes from the passwd entry, and a shell
+  // that rejects an unknown flag exits on the spot, which is #208 all over again.
+  const shell = resolveLocalShell();
+  return `${shellescape(shell)}${loginShellArgs(shell)}`;
 }
 
 /**
@@ -775,9 +862,23 @@ export function buildRemoteLaunchCommand(options: {
   mode: SessionMode;
   remote: SessionRemote;
   sessionId: string;
+  claudeMode?: ClaudeMode;
+  allowedTools?: string;
 }): string {
-  const { mode, remote, sessionId } = options;
-  const modeCommand = remote.commands?.[mode] || defaultRemoteCommandForMode(mode);
+  const { mode, remote, sessionId, claudeMode, allowedTools } = options;
+  // §6.3: honor the session's EFFECTIVE claude permission mode on remote instead of
+  // hardcoding --dangerously-skip-permissions, so a non-granted multi-user user's
+  // downgraded 'auto' actually reaches the remote agent (the default command otherwise
+  // ignored claudeMode). A per-host `commands.claude` override stays authoritative
+  // (admin's explicit choice). Wrapped in `$SHELL -i -l -c` for the same reason as
+  // `defaultRemoteCommandForMode`: `claude` lives under a per-user PATH entry that
+  // only an interactive login shell resolves (see that function's comment).
+  const override = remote.commands?.[mode];
+  const modeCommand = override
+    ? override
+    : mode === 'claude'
+      ? remoteLoginShellCommand(`claude${buildClaudePermissionFlags(claudeMode, allowedTools)}`)
+      : defaultRemoteCommandForMode(mode);
   const remoteName = remoteTmuxSessionName(sessionId);
 
   // Innermost: the command tmux runs in the new pane. Run via `/bin/sh -c` by
@@ -795,6 +896,31 @@ export function buildRemoteLaunchCommand(options: {
     `set -t ${remoteName} mouse off`,
     `set -t ${remoteName} prefix C-q`,
     'set -s escape-time 0',
+    // COD-106 — shared/collaborative sessions: tmux defaults to sizing a window
+    // to the SMALLEST attached client, so two Codemans at different viewports
+    // would fight (clamp to the smaller). `window-size latest` sizes to the
+    // most-recently-active client instead, so concurrent clients coexist.
+    // Per-session scoped (`set -t <name>`, matching #145's hardening) so a shared
+    // remote tmux server's other sessions keep their own sizing behavior.
+    `set -t ${remoteName} window-size latest`,
+    // #210: keep a CRASHED pane so the failure is still on screen. Without this,
+    // tmux destroys the pane -> window -> session (and, being the only session,
+    // the whole remote server) the instant the pane command exits, which tears the
+    // local `ssh -t` attach down with it; reconnect's `-A` then builds a fresh
+    // session and the cycle can repeat as a flap loop with no evidence surviving.
+    // That is how the exit-127 PATH bug fixed above stayed invisible.
+    //
+    // `failed`, NOT `on`: `on` keeps the pane on a CLEAN exit too, so typing
+    // `exit` in a remote shell leaves a dead pane behind, the session outlives it,
+    // and the next launch's `-A` reattaches to that corpse ("Pane is dead (status
+    // 0)") instead of starting a shell — verified against a real tmux. `failed`
+    // keeps the pane only on a non-zero exit, which is exactly the diagnostic case.
+    //
+    // LAST in the chain on purpose: tmux aborts the remaining commands of a `\;`
+    // sequence once one errors (also verified), and `failed` needs tmux >= 3.2 on
+    // the REMOTE host. Trailing, a rejection costs only this option; leading, it
+    // would silently drop status/mouse/prefix/escape-time/window-size with it.
+    `set -t ${remoteName} remain-on-exit failed`,
   ].join(' \\; ');
 
   // ssh runs its trailing args through the remote login shell, so the entire
@@ -856,24 +982,50 @@ export function dockerTmuxSessionName(sessionId: string): string {
 const RESUME_ID_SAFE = /^[A-Za-z0-9._-]+$/;
 
 /**
- * Append the CLI-specific resume flag to a pane command. Only fires when the
- * in-container tmux is RE-CREATED (`new-session -A` makes the flag inert on a
- * live reattach), i.e. exactly when the previous live agent was lost and we want
- * to resume the conversation from the bind-mounted transcript.
+ * Append the CLI-specific resume flag to a pane command (codex/gemini). Only fires
+ * when the in-container tmux is RE-CREATED (`new-session -A` makes the flag inert
+ * on a live reattach), i.e. exactly when the previous live agent was lost and we
+ * want to resume the conversation from the bind-mounted transcript. Claude mode
+ * uses claudeDockerPaneCommand instead.
  */
 function appendResumeFlag(modeCommand: string, mode: SessionMode, resumeId: string): string {
   if (!RESUME_ID_SAFE.test(resumeId)) return modeCommand;
   switch (mode) {
-    case 'claude':
     case 'gemini':
       return `${modeCommand} --resume ${resumeId}`;
     case 'codex':
       return `${modeCommand} resume ${resumeId}`;
+    case 'antigravity':
+      return `${modeCommand} --conversation ${resumeId}`;
     default:
       return modeCommand; // shell / opencode: no resume
   }
 }
 
+/**
+ * Claude-mode pane command with a DETERMINISTIC conversation id (the docker analog
+ * of buildSpawnCommand's --resume/--session-id logic). A fresh launch passes
+ * `--session-id <sessionId>`, so the in-container conversation id is knowable
+ * host-side (resume-id capture + subagent/workflow correlation) WITHOUT relying on
+ * hook reachability. When the in-container tmux was re-created after a container
+ * stop/reboot, the same command re-runs against the surviving transcript:
+ * `--session-id` exits 1 ("already in use") and the `||` fallback RESUMES that
+ * conversation (verified CLI behavior). An explicit resumeId gets the local
+ * builder's shape — resume first, session-id fallback — so a stale id never
+ * dead-panes. The leading `exec ` is stripped: an exec'd first branch could never
+ * fall back.
+ */
+function claudeDockerPaneCommand(modeCommand: string, sessionId: string, resumeId?: string): string {
+  if (!RESUME_ID_SAFE.test(sessionId)) return modeCommand; // defensive — ids are server-minted uuids
+  const cmd = modeCommand.replace(/^exec\s+/, '');
+  const rid = resumeId && RESUME_ID_SAFE.test(resumeId) ? resumeId : undefined;
+  if (rid && rid !== sessionId) {
+    return `${cmd} --resume ${rid} || ${cmd} --session-id ${sessionId}`;
+  }
+  const cid = rid ?? sessionId;
+  return `${cmd} --session-id ${cid} || ${cmd} --resume ${cid}`;
+}
+
 /** Fully-resolved inputs for buildDockerLaunchCommand (pure). */
 export interface DockerLaunchOptions {
   mode: SessionMode;
@@ -885,6 +1037,14 @@ export interface DockerLaunchOptions {
   execEnv: Record<string, string>;
   /** exec-time NAME-ONLY env forwarded from Codeman's process env (codex/gemini keys) */
   execEnvNames: string[];
+  /**
+   * Files to copy from read-only seed mounts into the container's writable HOME once
+   * before launch (guarded so reconnects never clobber). Isolates Claude state: the
+   * merged `~/.claude.json`, plus `~/.claude/.credentials.json` + `settings.json`,
+   * are writable copies (not host mounts), so the container never re-auths and never
+   * writes its runtime state back into the host `~/.claude`.
+   */
+  seedCopies?: DockerSeedCopy[];
 }
 
 /**
@@ -895,7 +1055,7 @@ export interface DockerLaunchOptions {
  * command -> `docker exec … sh -lc '<tmux>'` -> tmux `'<paneCommand>'`.
  */
 export function buildDockerLaunchCommand(opts: DockerLaunchOptions): string {
-  const { mode, docker, sessionId, resumeSessionId, createContext, execEnv, execEnvNames } = opts;
+  const { mode, docker, sessionId, resumeSessionId, createContext, execEnv, execEnvNames, seedCopies } = opts;
   const base = buildDockerBaseArgs(docker).join(' ');
   const createArgs = buildDockerCreateArgs(createContext).join(' ');
   const name = shellescape(docker.containerName);
@@ -905,7 +1065,11 @@ export function buildDockerLaunchCommand(opts: DockerLaunchOptions): string {
   const sid = sessionId.slice(0, 8);
 
   let modeCommand = docker.commands?.[mode as DockerCommandMode] || defaultDockerCommandForMode(mode);
-  if (resumeSessionId) modeCommand = appendResumeFlag(modeCommand, mode, resumeSessionId);
+  if (mode === 'claude') {
+    modeCommand = claudeDockerPaneCommand(modeCommand, sessionId, resumeSessionId);
+  } else if (resumeSessionId) {
+    modeCommand = appendResumeFlag(modeCommand, mode, resumeSessionId);
+  }
   // Run by tmux via /bin/sh -c, so the path is shell-quoted here. `exec` makes the
   // pane PID the agent itself.
   const paneCommand = `cd ${workdir} && ${modeCommand}`;
@@ -932,7 +1096,7 @@ export function buildDockerLaunchCommand(opts: DockerLaunchOptions): string {
   for (const extra of docker.extraExecArgs ?? []) execEnvFlags.push(shellescape(extra));
 
   const imageMissingMsg = shellescape(
-    `Codeman: base image ${docker.image} not present (build: node scripts/build-agent-image.mjs)`
+    `Codeman: base image ${docker.image} not present (it is normally auto-built on first use)`
   );
   const startFailMsg = shellescape(`Codeman: container ${docker.containerName} failed to start (docker daemon down?)`);
 
@@ -940,7 +1104,18 @@ export function buildDockerLaunchCommand(opts: DockerLaunchOptions): string {
   // create-if-missing (idempotent): reconnect / boot recovery re-runs this exact chain.
   const ensure = `${base} inspect ${name} >/dev/null 2>&1 || ${base} ${createArgs}`;
   const start = `${base} start ${name} >/dev/null 2>&1 || { echo ${startFailMsg}; exit 1; }`;
-  const execCmd = `exec ${base} exec -it --workdir ${workdir} ${execEnvFlags.join(' ')} ${name} sh -lc ${shellescape(tmuxInvocation)}`;
+  // Seed writable credential config from read-only host mounts ONCE per container
+  // (guarded by [ -e ] so reconnects never clobber in-container config; `cp -a` for
+  // whole-dir credential seeds). mkdir -p the parent so a file seed works even when
+  // no sibling share-mount pre-created the dir. Paths are fixed CONTAINER_HOME
+  // constants (no shell metachars), so the whole inner command is shell-quoted once.
+  const seedSteps = (seedCopies ?? []).map((s) => {
+    const cp = s.recursive ? 'cp -a' : 'cp';
+    const parent = s.to.slice(0, s.to.lastIndexOf('/'));
+    return `mkdir -p ${parent} 2>/dev/null; [ -e ${s.to} ] || ${cp} ${s.from} ${s.to} 2>/dev/null || true`;
+  });
+  const innerCmd = seedSteps.length ? `${seedSteps.join(' ; ')} ; ${tmuxInvocation}` : tmuxInvocation;
+  const execCmd = `exec ${base} exec -it --workdir ${workdir} ${execEnvFlags.join(' ')} ${name} sh -lc ${shellescape(innerCmd)}`;
 
   return [imageCheck, ensure, start, execCmd].join(' ; ');
 }
@@ -991,12 +1166,29 @@ export function resolveDockerLaunchOptions(
         : ['--user', `${uid}:0`]; // Linux: host uid + GID 0 (OpenShift arbitrary-uid writable HOME)
   const gatewayAlias = hostGatewayAlias(docker.engine);
 
-  const credentialMounts: DockerMount[] = docker.mountCredentials ? resolveCredentialMounts(home) : [];
+  const credentialMounts: DockerMount[] = [];
   const extraMounts: DockerMount[] = [];
+  // Isolated credential state (Claude + codex/gemini/gcloud/opencode): each store
+  // shares ONLY what a host feature / --resume needs (Claude projects/, codex
+  // sessions/+history) and seeds everything else (tokens, settings, configs) as
+  // writable copies, so the container is authed WITHOUT re-auth and WITHOUT writing
+  // its runtime state back into the host dirs. Only when credentials are mounted.
+  let seedCopies: DockerSeedCopy[] = [];
+  if (docker.mountCredentials) {
+    const claudeArtifacts = resolveDockerClaudeArtifacts(home, docker.containerName, docker.containerWorkdir);
+    const credArtifacts = resolveDockerCredentialArtifacts(home);
+    extraMounts.push(...claudeArtifacts.mounts, ...credArtifacts.mounts);
+    seedCopies = [...claudeArtifacts.seedCopies, ...credArtifacts.seedCopies];
+  }
   const envCreate: Record<string, string> = {
     HOME: CONTAINER_HOME,
     TERM: 'xterm-256color',
     COLORTERM: 'truecolor',
+    // Force a UTF-8 locale (the base image defaults to POSIX/C). Without this, tmux
+    // runs in non-UTF-8 mode and renders Claude's Unicode box-drawing (─│┌┐) as raw
+    // VT100 ACS glyphs (`qqqq…`). `C.UTF-8` is built into glibc (no locale-gen).
+    LANG: 'C.UTF-8',
+    LC_ALL: 'C.UTF-8',
     // Give claude a temp dir it will own inside HOME. Its default `/tmp/claude-<uid>`
     // is refused when that path pre-exists root-owned — which happens when the
     // workspace bind-mount path traverses it (e.g. a workspace under /tmp/claude-<uid>).
@@ -1031,6 +1223,11 @@ export function resolveDockerLaunchOptions(
   const execEnv: Record<string, string> = {
     TERM: 'xterm-256color',
     COLORTERM: 'truecolor',
+    // UTF-8 at exec time too, so the tmux CLIENT this exec launches is UTF-8 and
+    // renders box-drawing correctly even when reattaching to a container created
+    // before this fix (client_utf8 is per-client, resolved from the exec's locale).
+    LANG: 'C.UTF-8',
+    LC_ALL: 'C.UTF-8',
     CODEMAN_SESSION_ID: sessionId.slice(0, 8),
     CODEMAN_MUX: '1',
   };
@@ -1043,7 +1240,57 @@ export function resolveDockerLaunchOptions(
         ? ['GEMINI_API_KEY', 'GOOGLE_API_KEY']
         : [];
 
-  return { mode, docker, sessionId, resumeSessionId, createContext, execEnv, execEnvNames };
+  return { mode, docker, sessionId, resumeSessionId, createContext, execEnv, execEnvNames, seedCopies };
+}
+
+/**
+ * COD-105 — build the SSH command that ATTACHES to an EXISTING `codeman-*` tmux
+ * session on the remote host (one this Codeman didn't create — discovered via
+ * `listRemoteCodemanSessions`). Sibling of `buildRemoteLaunchCommand`.
+ *
+ * Emits:
+ *   ssh -o BatchMode=yes -t [<COD-107 connection opts>] user@host \
+ *     'tmux -L codeman attach -t <session>'
+ *
+ * - `attach` (NOT `new-session -A`) so we only join an existing session; the
+ *   remote session keeps running independent of us, which is exactly why the
+ *   resulting Codeman session is NON-OWNED (see `SessionRemote.owned`): closing
+ *   the local tab must detach, never `kill-session` the remote.
+ * - The remote session name is shell-escaped so a value with metachars stays a
+ *   single token inside the quoted tmux invocation.
+ * - COD-107 — connection options (`-p`, `-i`, `-J`, SOCKS `-o ProxyCommand`,
+ *   arbitrary `-o`) come from the shared `buildSshConnectionArgs`, so attach
+ *   connects identically to launch / discovery / the prereq probe. `-t` sits
+ *   right after `ssh -o BatchMode=yes` (a PTY is required for interactive tmux).
+ */
+export function buildRemoteAttachCommand(remote: SessionRemote, remoteSessionName: string): string {
+  const tmuxInvocation = `tmux -L codeman attach -t ${shellescape(remoteSessionName)}`;
+  const [ssh, batchMode, ...connectionArgs] = buildSshConnectionArgs(remote);
+  const sshParts = [ssh, batchMode, '-t', ...connectionArgs, remoteSshTarget(remote), shellescape(tmuxInvocation)];
+  return sshParts.join(' ');
+}
+
+/**
+ * COD-105 — choose the right remote ssh command for a session's ownership:
+ *   - NON-owned (`remote.owned === false`): ATTACH to a discovered remote tmux
+ *     session by its EXISTING name (`remote.remoteSessionName`, falling back to
+ *     this session's deterministic name). We only join — never create.
+ *   - owned (default): LAUNCH/attach-or-create via `buildRemoteLaunchCommand`
+ *     (COD-104), which we then own and may explicitly kill.
+ */
+function buildRemoteSessionCommand(options: {
+  mode: SessionMode;
+  remote: SessionRemote;
+  sessionId: string;
+  claudeMode?: ClaudeMode;
+  allowedTools?: string;
+}): string {
+  const { remote, sessionId } = options;
+  if (remote.owned === false) {
+    const target = remote.remoteSessionName || remoteTmuxSessionName(sessionId);
+    return buildRemoteAttachCommand(remote, target);
+  }
+  return buildRemoteLaunchCommand(options);
 }
 
 /**
@@ -1199,6 +1446,17 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
   /** Track last-known pane count per session to avoid unnecessary tmux set-option calls */
   private lastPaneCount: Map<string, number> = new Map();
 
+  // ── COD-108 remote-reconnect watcher state ────────────────────────────────
+  /** Periodic watcher that re-establishes dropped remote sessions. */
+  private remoteReconnectInterval: NodeJS.Timeout | null = null;
+  /** Per-session backoff/attempt bookkeeping (sessionId → state). */
+  private reconnectState: Map<string, RemoteReconnectState> = new Map();
+  /**
+   * Sessions excluded from auto-reconnect because they are being intentionally
+   * torn down (killed/detached/stopping). A guarded session is NEVER revived.
+   */
+  private reconnectGuard: Set<string> = new Set();
+
   private trueColorConfigured = false;
 
   constructor() {
@@ -1307,8 +1565,10 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     const exports = [
       'export LANG=en_US.UTF-8',
       'export LC_ALL=en_US.UTF-8',
-      mode === 'codex' || mode === 'gemini' ? 'export COLORTERM=truecolor' : 'unset COLORTERM',
-      ...(mode === 'codex' || mode === 'gemini' ? ['unset NO_COLOR'] : []),
+      mode === 'codex' || mode === 'gemini' || mode === 'antigravity'
+        ? 'export COLORTERM=truecolor'
+        : 'unset COLORTERM',
+      ...(mode === 'codex' || mode === 'gemini' || mode === 'antigravity' ? ['unset NO_COLOR'] : []),
       // Stamp each Codex pane with a unique originator so the response-viewer
       // can locate THIS pane's rollout exactly — codex writes the value into
       // session_meta.originator of every rollout it creates. Without it,
@@ -1391,6 +1651,10 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       const dir = resolveGeminiDir();
       return { pathExport: dir ? `export PATH="${dir}:$PATH" && ` : '', dir };
     }
+    if (mode === 'antigravity') {
+      const dir = resolveAntigravityDir();
+      return { pathExport: dir ? `export PATH="${dir}:$PATH" && ` : '', dir };
+    }
     return { pathExport: '', dir: null };
   }
 
@@ -1438,12 +1702,14 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       openCodeConfig,
       codexConfig,
       geminiConfig,
+      antigravityConfig,
       resumeSessionId,
       envOverrides,
       effort,
       historyLimit = DEFAULT_TMUX_HISTORY_LIMIT,
       remote,
       docker,
+      owner,
     } = options;
     const muxName = `codeman-${sessionId.slice(0, 8)}`;
 
@@ -1464,6 +1730,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
         workingDir,
         remote,
         docker,
+        owner,
         mode,
         attached: false,
         name,
@@ -1487,6 +1754,11 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     if (mode === 'gemini' && !cliDir) {
       throw new Error('Gemini CLI not found. Install with: npm install -g @google/gemini-cli');
     }
+    if (mode === 'antigravity' && !cliDir) {
+      throw new Error(
+        'Antigravity CLI not found. Install with: curl -fsSL https://antigravity.google/cli/install.sh | bash'
+      );
+    }
 
     const envExportsStr = this.buildEnvExports(sessionId, muxName, mode).join(' && ');
 
@@ -1499,6 +1771,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       openCodeConfig,
       codexConfig,
       geminiConfig,
+      antigravityConfig,
       resumeSessionId,
       effort,
     });
@@ -1512,7 +1785,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       const fullCmd = docker
         ? buildDockerLaunchCommand(resolveDockerLaunchOptions(mode, docker, sessionId, resumeSessionId))
         : remote
-          ? buildRemoteLaunchCommand({ mode, remote, sessionId })
+          ? buildRemoteSessionCommand({ mode, remote, sessionId, claudeMode, allowedTools })
           : localFullCmd;
 
       // Create tmux session in three steps to handle cold-start (no server running)
@@ -1640,6 +1913,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
         workingDir,
         remote,
         docker,
+        owner,
         mode,
         attached: false,
         name,
@@ -1720,6 +1994,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       openCodeConfig,
       codexConfig,
       geminiConfig,
+      antigravityConfig,
       resumeSessionId,
       envOverrides,
       effort,
@@ -1757,6 +2032,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       openCodeConfig,
       codexConfig,
       geminiConfig,
+      antigravityConfig,
       resumeSessionId,
       effort,
     });
@@ -1766,7 +2042,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     const fullCmd = docker
       ? buildDockerLaunchCommand(resolveDockerLaunchOptions(mode, docker, sessionId, resumeSessionId))
       : remote
-        ? buildRemoteLaunchCommand({ mode, remote, sessionId })
+        ? buildRemoteSessionCommand({ mode, remote, sessionId, claudeMode, allowedTools })
         : localFullCmd;
 
     try {
@@ -1882,9 +2158,16 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       return false;
     }
 
+    // COD-108: an intentional kill/detach must NEVER be auto-revived by the
+    // remote-reconnect watcher. Guard BEFORE any teardown so a tick that fires
+    // mid-kill (especially the non-owned DETACH early-return below, where the
+    // dead local pane would otherwise look reconnectable) sees the guard.
+    this.guardRemoteReconnect(sessionId);
+
     // TEST MODE: Remove from memory only — NEVER touch real tmux sessions
     if (IS_TEST_MODE) {
       this.sessions.delete(sessionId);
+      this.clearRemoteReconnectState(sessionId);
       this.emit('sessionKilled', { sessionId });
       return true;
     }
@@ -1896,6 +2179,40 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       return false;
     }
 
+    // COD-105 — DETACH-NOT-KILL for NON-owned remote sessions.
+    //
+    // When this session was created by ATTACHING a remote tmux session another
+    // Codeman owns (`remote.owned === false`), closing the tab must NOT propagate
+    // a remote `tmux kill-session` — that would nuke work the remote's own
+    // Codeman (or another instance) still relies on. We tear down ONLY the LOCAL
+    // pane that holds the ssh client: killing the local ssh sends SIGHUP to its
+    // remote `tmux attach`, which DETACHES (the durable remote session survives).
+    //
+    // This early return is the structural guarantee: no code below this point
+    // (now or in future for owned sessions) can ever issue a remote kill-session
+    // for a non-owned session. The only `kill-session` we run is on OUR LOCAL
+    // socket (`this.tmux()` = `tmux -L codeman` on THIS host), which kills the
+    // local pane — it does NOT reach the REMOTE socket.
+    if (session.remote && session.remote.owned === false) {
+      console.log(`[TmuxManager] DETACH (non-owned remote): tearing down local pane only for ${session.muxName}`);
+      if (isValidMuxName(session.muxName)) {
+        try {
+          // Local socket only — detaches the remote session by killing the local ssh pane.
+          execSync(`${this.tmux()} kill-session -t "${session.muxName}" 2>/dev/null`, {
+            timeout: EXEC_TIMEOUT_MS,
+          });
+        } catch {
+          // Local pane may already be gone.
+        }
+      }
+      this.lastPaneCount.delete(session.muxName);
+      this.sessions.delete(sessionId);
+      this.clearRemoteReconnectState(sessionId);
+      this.saveSessions();
+      this.emit('sessionKilled', { sessionId });
+      return true;
+    }
+
     // Get current PID (may have changed)
     const currentPid = this.getPanePid(session.muxName) || session.pid;
 
@@ -2000,6 +2317,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
 
     this.lastPaneCount.delete(session.muxName);
     this.sessions.delete(sessionId);
+    this.clearRemoteReconnectState(sessionId);
     this.saveSessions();
     this.emit('sessionKilled', { sessionId });
 
@@ -2066,6 +2384,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       } else {
         dead.push(sessionId);
         this.sessions.delete(sessionId);
+        this.clearRemoteReconnectState(sessionId);
         this.emit('sessionDied', { sessionId });
       }
     }
@@ -2337,9 +2656,118 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     this.lastPaneCount.clear();
   }
 
+  // ── COD-108 remote-session auto-reconnect watcher ─────────────────────────
+
+  /**
+   * Start the remote-reconnect watcher (COD-108). Each tick, for every tracked
+   * session with `session.remote` whose local pane is DEAD, not intentionally
+   * guarded, and within its backoff budget, emit `remoteSessionDropped` so the
+   * session owner reattaches (re-running the idempotent remote command rejoins
+   * the durable remote tmux session). After the attempt cap, emit
+   * `remoteReconnectExhausted` once and go quiet.
+   *
+   * No-op tick body under `IS_TEST_MODE` (mirrors `startMouseModeSync`): tests
+   * drive the logic deterministically via {@link runRemoteReconnectTick}.
+   */
+  startRemoteReconnectWatcher(intervalMs: number = DEFAULT_REMOTE_RECONNECT_INTERVAL_MS): void {
+    if (this.remoteReconnectInterval) {
+      clearInterval(this.remoteReconnectInterval);
+    }
+    this.remoteReconnectInterval = setInterval(() => {
+      if (IS_TEST_MODE) return;
+      try {
+        this.runRemoteReconnectTick(Date.now(), isRemoteAutoReconnectEnabled());
+      } catch (err) {
+        console.error('[TmuxManager] Remote reconnect watcher error:', err);
+      }
+    }, intervalMs);
+  }
+
+  stopRemoteReconnectWatcher(): void {
+    if (this.remoteReconnectInterval) {
+      clearInterval(this.remoteReconnectInterval);
+      this.remoteReconnectInterval = null;
+    }
+  }
+
+  /**
+   * Run ONE watcher tick. Extracted (and given an injected `now`/`enabled`) so
+   * the reconnect logic is deterministically testable even though the live
+   * `setInterval` body no-ops under test mode. For each remote session it
+   * applies the pure {@link decideReconnect} decision and translates the result
+   * into events + backoff/state transitions. Public for tests + the watcher.
+   */
+  runRemoteReconnectTick(now: number, enabled: boolean): void {
+    for (const session of this.sessions.values()) {
+      if (!session.remote) continue;
+      const sessionId = session.sessionId;
+      const state = this.reconnectState.get(sessionId);
+      const action = decideReconnect({
+        session: {
+          sessionId,
+          isRemote: true,
+          paneDead: this.isPaneDead(session.muxName),
+        },
+        state,
+        guarded: this.reconnectGuard.has(sessionId),
+        enabled,
+        now,
+      });
+
+      if (action.kind === 'emit') {
+        const base = state ?? freshReconnectState();
+        // Mark in-flight + advance backoff BEFORE emitting so a re-entrant tick
+        // (or a synchronous listener) can never stack a second reconnect.
+        this.reconnectState.set(sessionId, { ...advanceBackoff(base, now), inFlight: true });
+        this.emit('remoteSessionDropped', { sessionId, attempt: action.attempt });
+      } else if (action.kind === 'exhaust') {
+        const base = state ?? freshReconnectState();
+        if (!base.exhaustedEmitted) {
+          this.reconnectState.set(sessionId, { ...base, exhausted: true, exhaustedEmitted: true });
+          this.emit('remoteReconnectExhausted', { sessionId });
+        }
+      }
+      // 'skip' → nothing to do.
+    }
+  }
+
+  /**
+   * Tell the watcher a reattach attempt for `sessionId` finished. On success,
+   * reset the backoff so the session is healthy again; on failure, just clear
+   * the in-flight flag so the next due tick can retry under the existing
+   * backoff schedule. Called by the session owner after `respawnPane`.
+   */
+  noteRemoteReconnect(sessionId: string, success: boolean): void {
+    if (success) {
+      this.reconnectState.set(sessionId, resetReconnectState());
+      return;
+    }
+    const state = this.reconnectState.get(sessionId);
+    if (state) this.reconnectState.set(sessionId, { ...state, inFlight: false });
+  }
+
+  /**
+   * Exclude a session from auto-reconnect (intentional teardown). Adds it to the
+   * guard set and drops any backoff state so a closed/killed tab — especially a
+   * non-owned remote DETACH — is never auto-revived. Idempotent.
+   */
+  guardRemoteReconnect(sessionId: string): void {
+    this.reconnectGuard.add(sessionId);
+    this.reconnectState.delete(sessionId);
+  }
+
+  /** Clear all per-session reconnect + guard state (e.g. when a session is removed). */
+  clearRemoteReconnectState(sessionId: string): void {
+    this.reconnectState.delete(sessionId);
+    this.reconnectGuard.delete(sessionId);
+  }
+
   destroy(): void {
     this.stopStatsCollection();
     this.stopMouseModeSync();
+    this.stopRemoteReconnectWatcher();
+    this.reconnectState.clear();
+    this.reconnectGuard.clear();
   }
 
   registerSession(session: MuxSession): void {

src/transcript-watcher.ts

@@ -40,6 +40,7 @@ interface TranscriptContentBlock {
   text?: string;
   name?: string;
   input?: Record<string, unknown>;
+  tool_use_id?: string;
   content?: string;
   is_error?: boolean;
 }
@@ -328,10 +329,7 @@ export class TranscriptWatcher extends EventEmitter {
         this.handleResultEntry(entry);
         break;
       case 'user':
-        // User message means new turn, reset some state
-        this.state.isComplete = false;
-        this.state.hasError = false;
-        this.state.errorMessage = null;
+        this.handleUserEntry(entry);
         break;
       case 'system':
         // System messages are informational
@@ -360,23 +358,42 @@ export class TranscriptWatcher extends EventEmitter {
           this.state.currentTool = block.name;
           this.emit('transcript:tool_start', block.name);
         } else if (block.type === 'tool_result') {
-          // Tool completed
-          const wasError = block.is_error === true;
-          const toolName = this.state.currentTool;
-          this.state.toolExecuting = false;
-          this.state.currentTool = null;
-          if (toolName) {
-            this.emit('transcript:tool_end', toolName, wasError);
-          }
-          if (wasError && block.content) {
-            this.state.hasError = true;
-            this.state.errorMessage = String(block.content).slice(0, 200);
-          }
+          this.handleToolResult(block);
         }
       }
     }
   }
 
+  private handleUserEntry(entry: TranscriptEntry): void {
+    // A user-authored prompt starts a turn, while Claude tool results also use
+    // user entries. Reset turn state first, then close any completed tool.
+    this.state.isComplete = false;
+    this.state.hasError = false;
+    this.state.errorMessage = null;
+
+    const content = entry.message?.content;
+    if (!Array.isArray(content)) return;
+    for (const block of content) {
+      if (block.type === 'tool_result') {
+        this.handleToolResult(block);
+      }
+    }
+  }
+
+  private handleToolResult(block: TranscriptContentBlock): void {
+    const wasError = block.is_error === true;
+    const toolName = this.state.currentTool;
+    this.state.toolExecuting = false;
+    this.state.currentTool = null;
+    if (toolName) {
+      this.emit('transcript:tool_end', toolName, wasError);
+    }
+    if (wasError && block.content) {
+      this.state.hasError = true;
+      this.state.errorMessage = String(block.content).slice(0, 200);
+    }
+  }
+
   private handleResultEntry(entry: TranscriptEntry): void {
     // Result entry indicates completion
     this.state.isComplete = true;

src/tunnel-manager.ts

@@ -15,10 +15,8 @@
 
 import { EventEmitter } from 'node:events';
 import { spawn, type ChildProcess } from 'node:child_process';
-import { existsSync } from 'node:fs';
-import { join } from 'node:path';
-import { homedir } from 'node:os';
 import { randomBytes } from 'node:crypto';
+import { resolveCloudflaredPath } from './utils/cloudflared-resolver.js';
 import {
   QR_TOKEN_TTL_MS,
   QR_TOKEN_GRACE_MS,
@@ -43,6 +41,8 @@ interface QrTokenRecord {
   shortCode: string; // 6 chars base62 (for URL path)
   createdAt: number; // Date.now()
   consumed: boolean; // single-use flag
+  /** Multi-user: the user this token logs in when redeemed (absent = rotating global token). */
+  username?: string;
 }
 
 /** Rejection-sampled base62 short code — no modulo bias */
@@ -93,23 +93,10 @@ export class TunnelManager extends EventEmitter {
   private resolveCloudflared(): string | null {
     if (this.cloudflaredPath) return this.cloudflaredPath;
 
-    // Check ~/.local/bin first (common user install location)
-    const localBin = join(homedir(), '.local', 'bin', 'cloudflared');
-    if (existsSync(localBin)) {
-      this.cloudflaredPath = localBin;
-      return localBin;
-    }
-
-    // Check /usr/local/bin
-    const usrLocalBin = '/usr/local/bin/cloudflared';
-    if (existsSync(usrLocalBin)) {
-      this.cloudflaredPath = usrLocalBin;
-      return usrLocalBin;
-    }
-
-    // Fall back to PATH
-    this.cloudflaredPath = 'cloudflared';
-    return 'cloudflared';
+    // Shared with the welcome-screen availability check, so the button and the
+    // spawn can never disagree about where cloudflared lives.
+    this.cloudflaredPath = resolveCloudflaredPath() ?? 'cloudflared';
+    return this.cloudflaredPath;
   }
 
   /** Clear all pending timers */
@@ -378,23 +365,64 @@ export class TunnelManager extends EventEmitter {
    * Map.get() is hash-based — no timing side-channel from string comparison.
    */
   consumeToken(shortCode: string): boolean {
+    return this.consumeTokenWithIdentity(shortCode).ok;
+  }
+
+  /**
+   * Like consumeToken, but also returns the bound username for multi-user tokens
+   * (undefined for the rotating global token). Only the identity-less rotating
+   * token triggers an immediate re-rotation (desktop gets a fresh QR); per-user
+   * tokens are on-demand and self-expire.
+   */
+  consumeTokenWithIdentity(shortCode: string): { ok: boolean; username?: string } {
     // Global rate limit (across all IPs)
-    if (this.qrAttemptCount >= QR_RATE_LIMIT_MAX) return false;
+    if (this.qrAttemptCount >= QR_RATE_LIMIT_MAX) return { ok: false };
     this.qrAttemptCount++;
 
     const record = this.qrTokensByCode.get(shortCode);
-    if (!record) return false;
-    if (record.consumed) return false;
+    if (!record) return { ok: false };
+    if (record.consumed) return { ok: false };
 
     const now = Date.now();
-    if (now - record.createdAt > QR_TOKEN_GRACE_MS) return false;
+    if (now - record.createdAt > QR_TOKEN_GRACE_MS) return { ok: false };
 
     // Atomic consume (single-threaded JS = no race)
     record.consumed = true;
-    // Immediately rotate so desktop gets a fresh QR
-    this.rotateToken();
-    this.emit('qrTokenRegenerated');
-    return true;
+    const username = record.username;
+    if (!username) {
+      // Rotating global token — immediately rotate so desktop gets a fresh QR.
+      this.rotateToken();
+      this.emit('qrTokenRegenerated');
+    } else {
+      this.qrTokensByCode.delete(shortCode);
+    }
+    return { ok: true, username };
+  }
+
+  /**
+   * Multi-user: mint a single-use token bound to a specific user (on-demand, no
+   * rotation). Evicts expired/consumed tokens first. Returns the short code.
+   */
+  mintUserToken(username: string): string {
+    const now = Date.now();
+    for (const [code, rec] of this.qrTokensByCode) {
+      if (now - rec.createdAt > QR_TOKEN_GRACE_MS || rec.consumed) this.qrTokensByCode.delete(code);
+    }
+    const record: QrTokenRecord = {
+      token: randomBytes(32).toString('hex'),
+      shortCode: generateShortCode(),
+      createdAt: Date.now(),
+      consumed: false,
+      username,
+    };
+    this.qrTokensByCode.set(record.shortCode, record);
+    return record.shortCode;
+  }
+
+  /** Render a QR SVG for an arbitrary short code (used by per-user minting). */
+  async getQrSvgForCode(tunnelUrl: string, code: string): Promise<string> {
+    const QRCode = await import('qrcode');
+    return QRCode.toString(`${tunnelUrl}/q/${code}`, { type: 'svg', margin: 2, width: 256 });
   }
 
   /** Force-regenerate (manual revocation via API) */

src/types/api.ts

@@ -37,6 +37,16 @@ export enum ApiErrorCode {
   RATE_LIMITED = 'RATE_LIMITED',
   /** Operation could not be completed (well-formed but unprocessable) */
   OPERATION_FAILED = 'OPERATION_FAILED',
+  /** Authenticated but not permitted (e.g. non-admin hitting an admin route) */
+  FORBIDDEN = 'FORBIDDEN',
+  /** User must change their password before any other action (multi-user) */
+  PASSWORD_CHANGE_REQUIRED = 'PASSWORD_CHANGE_REQUIRED',
+  /** A user with this name already exists (multi-user) */
+  USER_EXISTS = 'USER_EXISTS',
+  /** No user with this name (multi-user) */
+  USER_NOT_FOUND = 'USER_NOT_FOUND',
+  /** Refusing to demote/disable/delete the last enabled admin (multi-user) */
+  LAST_ADMIN = 'LAST_ADMIN',
   /** Internal server error */
   INTERNAL_ERROR = 'INTERNAL_ERROR',
 }
@@ -53,6 +63,11 @@ const ErrorMessages: Record<ApiErrorCode, string> = {
   [ApiErrorCode.ALREADY_EXISTS]: 'Resource already exists',
   [ApiErrorCode.RATE_LIMITED]: 'Too many requests',
   [ApiErrorCode.OPERATION_FAILED]: 'The operation failed',
+  [ApiErrorCode.FORBIDDEN]: 'You do not have permission to perform this action',
+  [ApiErrorCode.PASSWORD_CHANGE_REQUIRED]: 'You must change your password before continuing',
+  [ApiErrorCode.USER_EXISTS]: 'A user with that name already exists',
+  [ApiErrorCode.USER_NOT_FOUND]: 'No such user',
+  [ApiErrorCode.LAST_ADMIN]: 'Cannot remove the last enabled admin',
   [ApiErrorCode.INTERNAL_ERROR]: 'An internal error occurred',
 };
 
@@ -69,6 +84,11 @@ const ErrorStatus: Record<ApiErrorCode, number> = {
   [ApiErrorCode.CONFLICT]: 409,
   [ApiErrorCode.ALREADY_EXISTS]: 409,
   [ApiErrorCode.OPERATION_FAILED]: 422,
+  [ApiErrorCode.FORBIDDEN]: 403,
+  [ApiErrorCode.PASSWORD_CHANGE_REQUIRED]: 403,
+  [ApiErrorCode.USER_EXISTS]: 409,
+  [ApiErrorCode.USER_NOT_FOUND]: 404,
+  [ApiErrorCode.LAST_ADMIN]: 409,
   [ApiErrorCode.RATE_LIMITED]: 429,
   [ApiErrorCode.INTERNAL_ERROR]: 500,
 };

src/types/app-state.ts

@@ -116,6 +116,8 @@ export interface AppState {
   cronJobs?: Record<string, CronJob>;
   /** Scheduled job run history, keyed by run ID. */
   cronJobRuns?: Record<string, CronJobRun>;
+  /** Global tab order shared across devices (ordered list of sessionIds) — COD-131 */
+  sessionOrder?: string[];
 }
 
 // ========== Default Configuration ==========

src/types/common.ts

@@ -9,6 +9,7 @@
  * - CleanupRegistration / CleanupResourceType — entries for the centralized CleanupManager
  * - NiceConfig / DEFAULT_NICE_CONFIG — process priority settings for `nice`/`ionice`
  * - ProcessStats — memory/CPU/child-count snapshot for resource monitoring
+ * - FilesystemBrowseData — bounded path-picker directory listing returned to the web UI
  */
 
 /**
@@ -68,6 +69,34 @@ export interface ProcessStats {
   updatedAt: number;
 }
 
+/** A selectable entry returned by the filesystem path-picker API. */
+export type FilesystemPreviewKind = 'image' | 'text' | 'document';
+
+export interface FilesystemBrowseEntry {
+  name: string;
+  path: string;
+  type: 'file' | 'directory';
+  size?: number;
+  symlink?: boolean;
+  previewKind?: FilesystemPreviewKind;
+}
+
+/** A named root the path picker may browse without escaping its allowlist. */
+export interface FilesystemBrowseRoot {
+  label: string;
+  path: string;
+}
+
+/** Response payload for `GET /api/filesystem/browse`. */
+export interface FilesystemBrowseData {
+  path: string;
+  parent: string | null;
+  root: string;
+  roots: FilesystemBrowseRoot[];
+  entries: FilesystemBrowseEntry[];
+  truncated: boolean;
+}
+
 export type CleanupResourceType = 'timer' | 'interval' | 'watcher' | 'listener' | 'stream';
 
 /**

src/types/cron.ts

@@ -36,6 +36,8 @@ export type ConcurrencyPolicy = 'warn_only' | 'skip_if_same_agent_running';
 export interface CronJob {
   id: string;
   name: string;
+  /** Owning username in multi-user mode; the job launches as this user. Undefined in single-user. */
+  owner?: string;
   /** Reuses Codeman's existing session modes; 'shell' covers Terminal/custom. */
   agentType: SessionMode;
   workingDir: string;

src/types/index.ts

@@ -69,3 +69,5 @@ export * from './orchestrator.js';
 export * from './update.js';
 export * from './workflow-run.js';
 export * from './search.js';
+export * from './user.js';
+export * from './webview.js';

src/types/session.ts

@@ -8,12 +8,13 @@
  * - SessionConfig — creation-time config (id, workingDir, createdAt)
  * - SessionOutput — captured stdout/stderr/exitCode
  * - SessionStatus — 'idle' | 'busy' | 'stopped' | 'error'
- * - SessionMode — 'claude' | 'shell' | 'opencode' | 'codex' | 'gemini' (which CLI backend)
- * - ClaudeMode — CLI permission mode ('dangerously-skip-permissions' | 'normal' | 'allowedTools')
+ * - SessionMode — 'claude' | 'shell' | 'opencode' | 'codex' | 'gemini' | 'antigravity' (which CLI backend)
+ * - ClaudeMode — CLI permission mode ('dangerously-skip-permissions' | 'auto' | 'normal' | 'allowedTools')
  * - SessionColor — visual differentiation color
  * - OpenCodeConfig — OpenCode-specific settings (model, autoAllowTools, continueSession)
  * - CodexConfig — Codex (OpenAI CLI)-specific settings (model, resumeSessionId)
  * - GeminiConfig — Gemini CLI-specific settings (model, approvalMode, resumeSession)
+ * - AntigravityConfig — Antigravity CLI (agy) settings (model, dangerouslySkipPermissions, resumeConversationId)
  *
  * Cross-domain relationships:
  * - SessionState.respawnConfig embeds RespawnConfig (respawn domain)
@@ -35,15 +36,19 @@ export type SessionStatus = 'idle' | 'busy' | 'stopped' | 'error';
 /**
  * Claude CLI startup permission mode.
  * - `'dangerously-skip-permissions'`: Bypass all permission prompts (default)
+ * - `'auto'`: Anthropic's classifier-guarded low-prompt mode (`--permission-mode auto`)
  * - `'normal'`: Standard mode with permission prompts
  * - `'allowedTools'`: Only allow specific tools (requires allowedTools list)
  */
-export type ClaudeMode = 'dangerously-skip-permissions' | 'normal' | 'allowedTools';
+export type ClaudeMode = 'dangerously-skip-permissions' | 'auto' | 'normal' | 'allowedTools';
 
 /** Session mode: which CLI backend a session runs */
-export type SessionMode = 'claude' | 'shell' | 'opencode' | 'codex' | 'gemini';
+export type SessionMode = 'claude' | 'shell' | 'opencode' | 'codex' | 'gemini' | 'antigravity';
 
-export type RemoteCommandMode = Extract<SessionMode, 'shell' | 'claude' | 'opencode' | 'codex' | 'gemini'>;
+export type RemoteCommandMode = Extract<
+  SessionMode,
+  'shell' | 'claude' | 'opencode' | 'codex' | 'gemini' | 'antigravity'
+>;
 
 /**
  * Advanced SSH connection options shared by RemoteHost and SessionRemote.
@@ -84,6 +89,8 @@ export interface RemoteHost extends RemoteSshOptions {
 export interface RemoteCase {
   name: string;
   type: 'remote';
+  /** Owning username in multi-user mode; absent = legacy/unassigned (admin-only). */
+  owner?: string;
   hostId: string;
   remotePath: string;
 }
@@ -96,6 +103,45 @@ export interface SessionRemote extends RemoteSshOptions {
   port?: number;
   remotePath: string;
   commands?: Partial<Record<RemoteCommandMode, string>>;
+  /**
+   * COD-105 — whether THIS Codeman created the remote tmux session.
+   *
+   * - `true` (default for COD-104 launched sessions): we own the remote session;
+   *   an explicit "kill" may propagate a remote `tmux kill-session`.
+   * - `false` (discovered + attached an existing remote session another Codeman
+   *   created): closing the local tab must DETACH only — we must NEVER issue a
+   *   remote `kill-session`, or we'd nuke work the remote's own Codeman (or
+   *   another instance) still relies on. See `killSession()` gate.
+   *
+   * Absent is treated as owned (legacy/COD-104 sessions persisted before this
+   * field existed were all launched by us).
+   */
+  owned?: boolean;
+  /**
+   * COD-105 — for a NON-owned (discovered + attached) session, the EXISTING
+   * remote tmux session name to `attach -t` (e.g. `codeman-disco1`). It differs
+   * from this Codeman's deterministic `codeman-<id>` name because the remote
+   * session was created elsewhere. Only meaningful when `owned === false`.
+   */
+  remoteSessionName?: string;
+}
+
+/**
+ * COD-105 — a `codeman-*` tmux session discovered on a remote host's
+ * `tmux -L codeman` socket (may have been created by the remote's own Codeman,
+ * another instance, or this one). Returned by `listRemoteCodemanSessions`.
+ */
+export interface RemoteSessionInfo {
+  /** tmux session name (always starts `codeman-`). */
+  name: string;
+  /** Whether at least one client is currently attached to the remote session. */
+  attached: boolean;
+  /** COD-106 — number of clients attached (tmux `session_attached`); >1 = shared. */
+  attachedClients: number;
+  /** tmux `session_created` epoch seconds. */
+  created: number;
+  /** Number of windows in the remote session. */
+  windows: number;
 }
 
 // ========== Docker cases (COD-Docker) ==========
@@ -108,7 +154,10 @@ export interface SessionRemote extends RemoteSshOptions {
 // into the same long-lived container. See `docs/docker-cases-plan.md`.
 
 /** Which CLI backends a Docker case can run (same set as remote). */
-export type DockerCommandMode = Extract<SessionMode, 'shell' | 'claude' | 'opencode' | 'codex' | 'gemini'>;
+export type DockerCommandMode = Extract<
+  SessionMode,
+  'shell' | 'claude' | 'opencode' | 'codex' | 'gemini' | 'antigravity'
+>;
 
 /** Container engine. Docker and Podman differ in the uid/userns + host-gateway alias. */
 export type DockerEngine = 'docker' | 'podman';
@@ -173,6 +222,8 @@ export interface DockerHost {
 export interface DockerCase {
   name: string;
   type: 'docker';
+  /** Owning username in multi-user mode; absent = legacy/unassigned (admin-only). */
+  owner?: string;
   hostId: string;
   /** Absolute HOST directory: the bind-mount source AND Session.workingDir (real host bytes). */
   hostWorkspacePath: string;
@@ -254,6 +305,8 @@ export interface CodexConfig {
   resumeSessionId?: string;
   /** Bypass approval prompts (passes --dangerously-bypass-approvals-and-sandbox) */
   dangerouslyBypassApprovals?: boolean;
+  /** Enable Codex's decorative TUI animations. Disable to reduce remote terminal redraws. */
+  animations?: boolean;
   /** Browser rendering strategy for Codex sessions. Hybrid TUI is the only supported mode. */
   renderMode?: CodexRenderMode;
 }
@@ -268,6 +321,16 @@ export interface GeminiConfig {
   resumeSession?: string;
 }
 
+/** Antigravity CLI (agy) session configuration */
+export interface AntigravityConfig {
+  /** Model identifier. Passed via --model. */
+  model?: string;
+  /** Auto-approve all tool permission requests (passes --dangerously-skip-permissions). Absent = agy's default prompting. */
+  dangerouslySkipPermissions?: boolean;
+  /** Resume a previous conversation by ID (passed via --conversation). */
+  resumeConversationId?: string;
+}
+
 /**
  * Configuration for creating a new session
  */
@@ -335,6 +398,8 @@ export interface SessionState {
   remote?: SessionRemote;
   /** Docker execution metadata, present when this session runs inside a container via local tmux + docker exec */
   docker?: SessionDocker;
+  /** Owning username in multi-user mode; undefined in single-user (ignored when the flag is off) */
+  owner?: string;
   /** ID of currently assigned task, null if none */
   currentTaskId: string | null;
   /** Timestamp when session was created */
@@ -359,6 +424,10 @@ export interface SessionState {
   autoResumeEnabled?: boolean;
   /** Pending usage-limit auto-resume fire time (epoch ms), if armed */
   autoResumeAt?: number;
+  /** Pinned to the top of the session manager list (COD-139) */
+  pinned?: boolean;
+  /** When the session was pinned (epoch ms) — orders the pinned group, most-recent-first */
+  pinnedAt?: number;
   /** Image watcher enabled for this session */
   imageWatcherEnabled?: boolean;
   /** Total cost in USD */
@@ -403,6 +472,8 @@ export interface SessionState {
   codexConfig?: CodexConfig;
   /** Gemini-specific configuration (only for mode === 'gemini') */
   geminiConfig?: GeminiConfig;
+  /** Antigravity-specific configuration (only for mode === 'antigravity') */
+  antigravityConfig?: AntigravityConfig;
   /** Claude conversation session ID to resume after reboot (set by restore script) */
   resumeSessionId?: string;
   /** Claude CLI effort level (soft default via --settings, switchable in-session via /effort) */

src/types/user.ts

@@ -0,0 +1,64 @@
+/**
+ * @fileoverview Multi-user mode types (opt-in `--multiuser`).
+ *
+ * Users live in `~/.codeman/users.json` (via `dataPath`, mode 0600). Each record
+ * carries a scrypt password hash with its own parameters so hashing cost can be
+ * raised later and old records rehashed on next login. `AuthUser` is the
+ * request-scoped identity decorated onto Fastify requests; in SINGLE-user mode a
+ * synthetic `{ username: 'admin', role: 'admin' }` is used so downstream code has
+ * one code path. See `src/user-store.ts` and `docs/multi-user-plan.md`.
+ */
+
+export type UserRole = 'admin' | 'user';
+
+/** Per-record scrypt parameters + salt/hash (all hex). */
+export interface PasswordHash {
+  algo: 'scrypt';
+  N: number;
+  r: number;
+  p: number;
+  salt: string;
+  hash: string;
+}
+
+export interface UserRecord {
+  /** Canonical lowercase slug; also the user's folder name under USER_SPACES_DIR. */
+  username: string;
+  role: UserRole;
+  password: PasswordHash;
+  /** Disabled accounts fail auth closed but keep their space on disk. */
+  disabled?: boolean;
+  /** Set by an admin reset; gates all API access until the user changes it. */
+  mustChangePassword?: boolean;
+  /**
+   * Permission-mode grant (section 6.3). When false (the default for new users),
+   * the user's Claude sessions are forced to `--permission-mode auto`, shell mode
+   * and cron `launchCommand` are refused, and other CLIs' bypass flags are dropped.
+   */
+  canBypassPermissions?: boolean;
+  createdAt: number;
+  lastLoginAt?: number;
+}
+
+/** On-disk shape of `users.json`. */
+export interface UsersFile {
+  version: 1;
+  users: UserRecord[];
+}
+
+/** Request-scoped identity (decorated as `req.authUser`). */
+export interface AuthUser {
+  username: string;
+  role: UserRole;
+}
+
+/** Admin-facing projection of a user: never carries the password hash. */
+export interface PublicUser {
+  username: string;
+  role: UserRole;
+  disabled: boolean;
+  mustChangePassword: boolean;
+  canBypassPermissions: boolean;
+  createdAt: number;
+  lastLoginAt?: number;
+}

src/types/webview.ts

@@ -0,0 +1,87 @@
+/**
+ * @fileoverview Web tab (dashboard) types.
+ *
+ * A "webview" is a saved URL that Codeman renders as a tab alongside agent
+ * sessions: Grafana on :3000, a Uptime-Kuma on :4000, an internal status page.
+ * It is deliberately NOT a sixth `SessionMode`, it has no PTY, no tmux, no
+ * respawn and no idle detection. Same reasoning that keeps Docker and remote-SSH
+ * as case overlays rather than modes.
+ *
+ * Key exports:
+ * - Webview, the persisted record (`~/.codeman/webviews.json`).
+ * - WebviewEmbedMode, 'proxy' (served through Codeman's origin) or 'direct'
+ *   (a plain cross-origin iframe, only viable for HTTPS targets that allow framing).
+ * - WebviewProbe, the result of the server-side reachability/framing probe.
+ * - WebviewOpenData, what `POST /api/webviews/:id/open` hands the browser.
+ *
+ * No I/O here. Persistence lives in `src/webview-store.ts`, capability minting in
+ * `src/webview-capabilities.ts`, the proxy helpers in `src/web/webview-proxy.ts`.
+ */
+
+/**
+ * How the browser should embed a webview.
+ *
+ * - `proxy`: the iframe points at `/webview/<capability>/` on Codeman's own
+ *   origin and the server relays to the target. Required whenever the target is
+ *   plain HTTP (an HTTPS Codeman page cannot embed it: mixed content) or refuses
+ *   framing via `X-Frame-Options` / `frame-ancestors`.
+ * - `direct`: the iframe points at the target URL itself. Cheaper, but only works
+ *   for HTTPS targets that permit framing, and needs the target origin added to
+ *   the page CSP's `frame-src`.
+ */
+export type WebviewEmbedMode = 'proxy' | 'direct';
+
+/** A saved dashboard, persisted to `~/.codeman/webviews.json`. */
+export interface Webview {
+  id: string;
+  /** Display name shown on the tab. */
+  name: string;
+  /** Absolute target URL. `http:` / `https:` only, never with embedded credentials. */
+  url: string;
+  /** Optional single-glyph tab icon (emoji or letter). */
+  icon?: string;
+  /** Default embed strategy for this dashboard. */
+  embedMode: WebviewEmbedMode;
+  /**
+   * When false (the default) the iframe is sandboxed WITHOUT `allow-same-origin`,
+   * so a proxied page runs in an opaque origin and cannot read the Codeman page or
+   * call its API. Setting this to true trades that isolation for the page's own
+   * cookies/localStorage, only for dashboards the user fully trusts.
+   */
+  trusted: boolean;
+  /** Multi-user owner (username). Undefined in single-user mode. */
+  owner?: string;
+  createdAt: number;
+  lastOpenedAt?: number;
+}
+
+/** Result of the server-side probe used by the "Test" button in the editor. */
+export interface WebviewProbe {
+  /** True when the server could complete an HTTP request to the target. */
+  reachable: boolean;
+  /** Upstream status code, when a response came back. */
+  status?: number;
+  /** Raw `X-Frame-Options` value, if the target sent one. */
+  xFrameOptions?: string;
+  /** The `frame-ancestors` directive extracted from the target's CSP, if any. */
+  frameAncestors?: string;
+  /** True when the target permits being framed cross-origin by this Codeman. */
+  framable: boolean;
+  /** Strategy the UI should default to for this URL. */
+  recommendedMode: WebviewEmbedMode;
+  /** Human-readable explanation of the recommendation (or the failure). */
+  reason: string;
+}
+
+/** Payload of `POST /api/webviews/:id/open`. */
+export interface WebviewOpenData {
+  /** The webview being opened (echoed so the client can refresh its copy). */
+  webview: Webview;
+  /**
+   * Same-origin path the iframe should load. Present for `proxy` mode only;
+   * `direct` mode uses `webview.url` instead.
+   */
+  embedUrl?: string;
+  /** Epoch ms at which the capability behind `embedUrl` stops working. */
+  expiresAt?: number;
+}

src/user-store.ts

@@ -0,0 +1,488 @@
+/**
+ * @fileoverview Multi-user store: `~/.codeman/users.json` (via `dataPath`, 0600).
+ *
+ * Mirrors the storage-module pattern of `remote-hosts.ts` / `docker-hosts.ts`, but
+ * because it holds password hashes it writes atomically (tmp + rename) at mode
+ * 0600 and keeps only a SHORT in-process cache so the CLI (`codeman users …`) can
+ * edit the file while the server runs and have changes picked up within the TTL.
+ *
+ * Pure, IO-free helpers (`isValidUsername`, `hashPassword`, `verifyPasswordHash`,
+ * `needsRehash`, `resolveClaudeModeForUser`, the last-admin invariants) are split
+ * out so they are unit-testable without a server. Hashing is `scrypt` from
+ * `node:crypto` (no new deps), compared via `timingSafeEqual`; parameters are
+ * stored per record so cost can be raised later and old records rehashed on their
+ * next successful login.
+ *
+ * See `docs/multi-user-plan.md` sections 4.1, 5, 6.3.
+ */
+
+import { existsSync, mkdirSync } from 'node:fs';
+import fs from 'node:fs/promises';
+import { isAbsolute, join, relative } from 'node:path';
+import { randomBytes, scrypt as scryptCb, timingSafeEqual } from 'node:crypto';
+import { promisify } from 'node:util';
+import { dataPath, getDataDir } from './config/instance.js';
+import { getUserSpacesDir, isMultiUserMode, maxUsers } from './config/multiuser.js';
+import type { AuthUser, ClaudeMode, PasswordHash, PublicUser, UserRecord, UserRole, UsersFile } from './types.js';
+
+const scrypt = promisify(scryptCb) as (
+  password: string | Buffer,
+  salt: string | Buffer,
+  keylen: number,
+  options: { N: number; r: number; p: number; maxmem: number }
+) => Promise<Buffer>;
+
+const USERS_FILE = 'users.json';
+const CACHE_TTL_MS = 1000;
+const KEYLEN = 64;
+const SALT_BYTES = 32;
+/** Generous ceiling so raising N/r later does not trip scrypt's memory guard. */
+const SCRYPT_MAXMEM = 256 * 1024 * 1024;
+
+/** Current hashing parameters. Stored per record; raise these to increase cost. */
+export const DEFAULT_SCRYPT_PARAMS = { N: 16384, r: 8, p: 1 } as const;
+
+/** Username: lowercase, first char alphanumeric, 2-32 chars total. Becomes a folder name. */
+const USERNAME_RE = /^[a-z0-9][a-z0-9_-]{1,31}$/;
+
+/** Typed error whose `.code` maps to an API errorCode at the route layer. */
+export class UserStoreError extends Error {
+  constructor(
+    message: string,
+    public readonly code: 'USER_EXISTS' | 'USER_NOT_FOUND' | 'LAST_ADMIN' | 'INVALID_INPUT'
+  ) {
+    super(message);
+    this.name = 'UserStoreError';
+  }
+}
+
+// ─────────────────────────────── pure helpers ───────────────────────────────
+
+export function normalizeUsername(name: string): string {
+  return String(name ?? '')
+    .trim()
+    .toLowerCase();
+}
+
+export function isValidUsername(name: string): boolean {
+  return USERNAME_RE.test(normalizeUsername(name));
+}
+
+/** Hash a password with the given (or current) scrypt params + a fresh random salt. */
+export async function hashPassword(
+  password: string,
+  params: { N: number; r: number; p: number } = DEFAULT_SCRYPT_PARAMS
+): Promise<PasswordHash> {
+  const salt = randomBytes(SALT_BYTES);
+  const derived = await scrypt(password, salt, KEYLEN, { ...params, maxmem: SCRYPT_MAXMEM });
+  return {
+    algo: 'scrypt',
+    N: params.N,
+    r: params.r,
+    p: params.p,
+    salt: salt.toString('hex'),
+    hash: derived.toString('hex'),
+  };
+}
+
+/** Constant-time verify of a password against a stored hash record. Never throws. */
+export async function verifyPasswordHash(password: string, record: PasswordHash): Promise<boolean> {
+  if (!record || record.algo !== 'scrypt') return false;
+  let salt: Buffer;
+  let expected: Buffer;
+  try {
+    salt = Buffer.from(record.salt, 'hex');
+    expected = Buffer.from(record.hash, 'hex');
+  } catch {
+    return false;
+  }
+  if (expected.length === 0) return false;
+  let derived: Buffer;
+  try {
+    derived = await scrypt(password, salt, expected.length, {
+      N: record.N,
+      r: record.r,
+      p: record.p,
+      maxmem: SCRYPT_MAXMEM,
+    });
+  } catch {
+    return false;
+  }
+  if (derived.length !== expected.length) return false;
+  return timingSafeEqual(derived, expected);
+}
+
+/** True when a stored hash uses weaker params than current and should be rehashed. */
+export function needsRehash(record: PasswordHash, params = DEFAULT_SCRYPT_PARAMS): boolean {
+  return record.algo !== 'scrypt' || record.N !== params.N || record.r !== params.r || record.p !== params.p;
+}
+
+/** URL-safe one-time password (16 chars) for admin create/reset flows. */
+export function generateOneTimePassword(): string {
+  return randomBytes(12).toString('base64url');
+}
+
+export function toPublicUser(u: UserRecord): PublicUser {
+  return {
+    username: u.username,
+    role: u.role,
+    disabled: !!u.disabled,
+    mustChangePassword: !!u.mustChangePassword,
+    canBypassPermissions: !!u.canBypassPermissions,
+    createdAt: u.createdAt,
+    lastLoginAt: u.lastLoginAt,
+  };
+}
+
+export function countEnabledAdmins(users: UserRecord[]): number {
+  return users.filter((u) => u.role === 'admin' && !u.disabled).length;
+}
+
+/**
+ * Section 6.3: resolve the effective Claude permission mode for a user. Admins and
+ * granted users get the global mode as-is; a non-granted regular user whose mode
+ * would be `dangerously-skip-permissions` is silently downgraded to `auto` (all
+ * other modes are already <= auto and pass through). Pure.
+ */
+export function resolveClaudeModeForUser(
+  globalMode: ClaudeMode | undefined,
+  grant: { role: UserRole; canBypassPermissions?: boolean }
+): ClaudeMode {
+  const mode: ClaudeMode = globalMode ?? 'dangerously-skip-permissions';
+  if (grant.role === 'admin' || grant.canBypassPermissions) return mode;
+  return mode === 'dangerously-skip-permissions' ? 'auto' : mode;
+}
+
+/**
+ * Section 6.3: whether a user may run arbitrary commands as the host account
+ * (shell-mode sessions, cron `launchCommand`, other CLIs' bypass flags). Same
+ * one-bit grant as bypass. Admins always may.
+ */
+export function canRunPrivilegedCommands(grant: { role: UserRole; canBypassPermissions?: boolean }): boolean {
+  return grant.role === 'admin' || !!grant.canBypassPermissions;
+}
+
+// ─────────────────────────────── IO layer ───────────────────────────────
+
+let cache: { users: UserRecord[]; ts: number } | null = null;
+
+/** Drop the in-process cache (called after every write; exported for tests). */
+export function invalidateUsersCache(): void {
+  cache = null;
+}
+
+export async function readUsers(force = false): Promise<UserRecord[]> {
+  const now = Date.now();
+  if (!force && cache && now - cache.ts < CACHE_TTL_MS) return cache.users;
+  let raw: string;
+  try {
+    raw = await fs.readFile(dataPath(USERS_FILE), 'utf-8');
+  } catch (err) {
+    // ENOENT is the ONLY legitimately-empty store (first boot). Any other read
+    // error (EIO/EACCES/EMFILE/EBUSY) is a transient/permission failure, NOT an
+    // empty store — do NOT cache [] and do NOT let it look empty, or a following
+    // createUser/bootstrap would overwrite users.json and destroy every account.
+    if ((err as NodeJS.ErrnoException).code === 'ENOENT') {
+      cache = { users: [], ts: now };
+      return [];
+    }
+    throw err;
+  }
+  // A present-but-corrupt file (invalid JSON) must also fail loud rather than
+  // read as empty, so mutators/bootstrap abort instead of clobbering it.
+  const parsed = JSON.parse(raw) as Partial<UsersFile>;
+  const users = Array.isArray(parsed.users) ? parsed.users : [];
+  cache = { users, ts: now };
+  return users;
+}
+
+async function writeUsers(users: UserRecord[]): Promise<void> {
+  const dir = getDataDir();
+  if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
+  const finalPath = dataPath(USERS_FILE);
+  // Unique per-writer tmp name (pid + random) so the CLI (`codeman users …`) and
+  // the live server — designed to write this file concurrently across processes —
+  // never share a single `users.json.tmp` inode and tear each other's payload.
+  // Matches the state-store.ts / self-update.ts convention.
+  const tmpPath = `${finalPath}.${process.pid}.${randomBytes(6).toString('hex')}.tmp`;
+  const payload: UsersFile = { version: 1, users };
+  try {
+    await fs.writeFile(tmpPath, JSON.stringify(payload, null, 2), { mode: 0o600 });
+    await fs.chmod(tmpPath, 0o600).catch(() => {});
+    await fs.rename(tmpPath, finalPath);
+  } catch (err) {
+    await fs.unlink(tmpPath).catch(() => {});
+    throw err;
+  }
+  cache = { users, ts: Date.now() };
+}
+
+/**
+ * Serialize every read-modify-write on users.json. Without this a fire-and-forget
+ * touchLastLogin (fired on each Basic auth) can interleave with a route's
+ * create/update and clobber records, since both do readUsers(true) → mutate →
+ * writeUsers against a single shared file + tmp path.
+ */
+let mutateChain: Promise<unknown> = Promise.resolve();
+function withUsersLock<T>(fn: () => Promise<T>): Promise<T> {
+  const run = mutateChain.then(fn, fn);
+  mutateChain = run.then(
+    () => undefined,
+    () => undefined
+  );
+  return run;
+}
+
+export async function hasUsers(): Promise<boolean> {
+  return (await readUsers()).length > 0;
+}
+
+// A precomputed dummy hash so an unknown/disabled user costs the same scrypt work
+// as a real verify (defeats username-enumeration by timing). Created once, lazily.
+let dummyHashPromise: Promise<PasswordHash> | null = null;
+function getDummyHash(): Promise<PasswordHash> {
+  if (!dummyHashPromise) dummyHashPromise = hashPassword('codeman-timing-equalization-placeholder');
+  return dummyHashPromise;
+}
+
+/**
+ * Verify a username/password against the store. Returns the record (plus whether it
+ * should be rehashed) on success, or null for wrong password / unknown / disabled
+ * user. Runs a dummy scrypt on the miss path so timing does not reveal which users
+ * exist. Never writes (the caller decides when to persist lastLogin / rehash).
+ */
+export async function verifyPassword(
+  username: string,
+  password: string
+): Promise<{ user: UserRecord; needsRehash: boolean } | null> {
+  const user = await findUser(username);
+  if (!user || user.disabled) {
+    await verifyPasswordHash(password, await getDummyHash());
+    return null;
+  }
+  const ok = await verifyPasswordHash(password, user.password);
+  if (!ok) return null;
+  return { user, needsRehash: needsRehash(user.password) };
+}
+
+export async function findUser(username: string): Promise<UserRecord | undefined> {
+  const norm = normalizeUsername(username);
+  if (!norm) return undefined;
+  const users = await readUsers();
+  return users.find((u) => u.username === norm);
+}
+
+export interface CreateUserOptions {
+  username: string;
+  role: UserRole;
+  password: string;
+  mustChangePassword?: boolean;
+  canBypassPermissions?: boolean;
+}
+
+export async function createUser(opts: CreateUserOptions): Promise<UserRecord> {
+  const username = normalizeUsername(opts.username);
+  if (!isValidUsername(username)) {
+    throw new UserStoreError(
+      'Username must be lowercase, start alphanumeric, 2-32 chars ([a-z0-9_-])',
+      'INVALID_INPUT'
+    );
+  }
+  if (opts.role !== 'admin' && opts.role !== 'user') {
+    throw new UserStoreError('Role must be "admin" or "user"', 'INVALID_INPUT');
+  }
+  if (!opts.password || opts.password.length < 8) {
+    throw new UserStoreError('Password must be at least 8 characters', 'INVALID_INPUT');
+  }
+  return withUsersLock(async () => {
+    const users = await readUsers(true);
+    if (users.some((u) => u.username === username)) {
+      throw new UserStoreError(`User "${username}" already exists`, 'USER_EXISTS');
+    }
+    if (users.length >= maxUsers()) {
+      throw new UserStoreError(`Maximum number of users (${maxUsers()}) reached`, 'INVALID_INPUT');
+    }
+    const record: UserRecord = {
+      username,
+      role: opts.role,
+      password: await hashPassword(opts.password),
+      disabled: false,
+      mustChangePassword: !!opts.mustChangePassword,
+      canBypassPermissions: !!opts.canBypassPermissions,
+      createdAt: Date.now(),
+    };
+    users.push(record);
+    await writeUsers(users);
+    return record;
+  });
+}
+
+/** Set a user's password. `mustChangePassword` is left unchanged unless specified. */
+export async function setPassword(
+  username: string,
+  password: string,
+  opts: { mustChangePassword?: boolean } = {}
+): Promise<UserRecord> {
+  if (!password || password.length < 8) {
+    throw new UserStoreError('Password must be at least 8 characters', 'INVALID_INPUT');
+  }
+  const norm = normalizeUsername(username);
+  return withUsersLock(async () => {
+    const users = await readUsers(true);
+    const record = users.find((u) => u.username === norm);
+    if (!record) throw new UserStoreError(`User "${norm}" not found`, 'USER_NOT_FOUND');
+    record.password = await hashPassword(password);
+    if (opts.mustChangePassword !== undefined) record.mustChangePassword = opts.mustChangePassword;
+    await writeUsers(users);
+    return record;
+  });
+}
+
+export interface UpdateUserPatch {
+  role?: UserRole;
+  disabled?: boolean;
+  canBypassPermissions?: boolean;
+  mustChangePassword?: boolean;
+}
+
+export async function updateUser(username: string, patch: UpdateUserPatch): Promise<UserRecord> {
+  const norm = normalizeUsername(username);
+  return withUsersLock(async () => {
+    const users = await readUsers(true);
+    const record = users.find((u) => u.username === norm);
+    if (!record) throw new UserStoreError(`User "${norm}" not found`, 'USER_NOT_FOUND');
+
+    // Guard the last-enabled-admin invariant against demote/disable.
+    const before = countEnabledAdmins(users);
+    const projected: UserRecord = {
+      ...record,
+      role: patch.role ?? record.role,
+      disabled: patch.disabled ?? record.disabled,
+    };
+    const after = countEnabledAdmins(users.map((u) => (u.username === norm ? projected : u)));
+    if (before > 0 && after === 0) {
+      throw new UserStoreError('Cannot demote or disable the last enabled admin', 'LAST_ADMIN');
+    }
+
+    if (patch.role !== undefined) record.role = patch.role;
+    if (patch.disabled !== undefined) record.disabled = patch.disabled;
+    if (patch.canBypassPermissions !== undefined) record.canBypassPermissions = patch.canBypassPermissions;
+    if (patch.mustChangePassword !== undefined) record.mustChangePassword = patch.mustChangePassword;
+    await writeUsers(users);
+    return record;
+  });
+}
+
+/**
+ * Record a successful login timestamp. Best-effort + throttled: skips the write if
+ * the last login was within the last minute (Basic clients re-send credentials on
+ * every request, so this fires often — the throttle keeps disk churn bounded).
+ */
+export async function touchLastLogin(username: string): Promise<void> {
+  const norm = normalizeUsername(username);
+  try {
+    await withUsersLock(async () => {
+      const users = await readUsers(true);
+      const record = users.find((u) => u.username === norm);
+      if (!record) return;
+      if (record.lastLoginAt && Date.now() - record.lastLoginAt < 60_000) return;
+      record.lastLoginAt = Date.now();
+      await writeUsers(users);
+    });
+  } catch {
+    /* best-effort */
+  }
+}
+
+export async function deleteUser(username: string): Promise<void> {
+  const norm = normalizeUsername(username);
+  await withUsersLock(async () => {
+    const users = await readUsers(true);
+    const record = users.find((u) => u.username === norm);
+    if (!record) throw new UserStoreError(`User "${norm}" not found`, 'USER_NOT_FOUND');
+    const before = countEnabledAdmins(users);
+    const remaining = users.filter((u) => u.username !== norm);
+    const after = countEnabledAdmins(remaining);
+    if (before > 0 && after === 0) {
+      throw new UserStoreError('Cannot delete the last enabled admin', 'LAST_ADMIN');
+    }
+    await writeUsers(remaining);
+  });
+}
+
+/**
+ * First-boot bootstrap: in multi-user mode with no users yet, create the initial
+ * admin from `CODEMAN_USERNAME`/`CODEMAN_PASSWORD` if both are set. Returns a
+ * status the caller (server start / CLI) uses to decide whether to refuse boot.
+ */
+export async function bootstrapInitialAdmin(): Promise<{
+  status: 'created' | 'exists' | 'missing-env';
+  username?: string;
+}> {
+  if (await hasUsers()) return { status: 'exists' };
+  const username = process.env.CODEMAN_USERNAME;
+  const password = process.env.CODEMAN_PASSWORD;
+  if (!username || !password) return { status: 'missing-env' };
+  const created = await createUser({ username, role: 'admin', password });
+  return { status: 'created', username: created.username };
+}
+
+/**
+ * Delete a user's on-disk space (`<USER_SPACES_DIR>/<username>`) with the section 8
+ * guard rails: the top-level dir must not be a symlink, and its realpath must
+ * resolve strictly inside USER_SPACES_DIR (so a symlinked or `..`-escaping target
+ * can never be used to rm an arbitrary tree). No-op if the space does not exist.
+ */
+export async function deleteUserSpace(username: string): Promise<void> {
+  const norm = normalizeUsername(username);
+  if (!isValidUsername(norm)) throw new UserStoreError('Invalid username', 'INVALID_INPUT');
+  const root = getUserSpacesDir();
+  const target = join(root, norm);
+  let lst;
+  try {
+    lst = await fs.lstat(target);
+  } catch {
+    return; // nothing to delete
+  }
+  if (lst.isSymbolicLink()) {
+    throw new UserStoreError('Refusing to delete a symlinked user space', 'INVALID_INPUT');
+  }
+  const realRoot = await fs.realpath(root).catch(() => root);
+  const realTarget = await fs.realpath(target);
+  const rel = relative(realRoot, realTarget);
+  if (rel === '' || rel.startsWith('..') || isAbsolute(rel)) {
+    throw new UserStoreError('User space escapes USER_SPACES_DIR', 'INVALID_INPUT');
+  }
+  await fs.rm(realTarget, { recursive: true, force: true });
+}
+
+/** The synthetic admin used in single-user mode so downstream has one code path. */
+export const SYNTHETIC_ADMIN: AuthUser = { username: 'admin', role: 'admin' };
+
+/**
+ * Whether a username may run arbitrary commands (shell mode, cron launchCommand,
+ * other CLIs' bypass). Single-user or an unset owner: allowed. In multi-user a
+ * MISSING user (e.g. deleted) fails closed (non-privileged). Used at cron fire time.
+ */
+export async function canUsernameRunPrivilegedCommands(username: string | undefined): Promise<boolean> {
+  if (!isMultiUserMode() || !username) return true;
+  const user = await findUser(username);
+  return canRunPrivilegedCommands(user ?? { role: 'user' });
+}
+
+/**
+ * Resolve the effective Claude mode for a username by looking up the grant. In
+ * single-user mode (or for an unknown owner) the global mode passes through.
+ */
+export async function resolveClaudeModeForUsername(
+  globalMode: ClaudeMode | undefined,
+  username: string | undefined
+): Promise<ClaudeMode> {
+  const fallback: ClaudeMode = globalMode ?? 'dangerously-skip-permissions';
+  if (!isMultiUserMode() || !username) return fallback;
+  // Fail closed: an unknown/deleted owner in multi-user mode is treated as a
+  // non-granted regular user so a stale-owned spawn (e.g. an orphaned cron job)
+  // is downgraded to `auto` rather than inheriting the global bypass.
+  const user = await findUser(username);
+  return resolveClaudeModeForUser(globalMode, user ?? { role: 'user' });
+}

src/utils/antigravity-cli-resolver.ts

@@ -0,0 +1,65 @@
+/**
+ * @fileoverview Resolve the Antigravity CLI (`agy`) binary across common install paths.
+ *
+ * Mirrors gemini-cli-resolver.ts. Google's installer (antigravity.google/cli/install.sh)
+ * places the binary at ~/.local/bin/agy; the other locations cover manual installs.
+ *
+ * @module utils/antigravity-cli-resolver
+ */
+
+import { execSync } from 'node:child_process';
+import { existsSync } from 'node:fs';
+import { dirname, join } from 'node:path';
+import { homedir } from 'node:os';
+import { EXEC_TIMEOUT_MS } from '../config/exec-timeout.js';
+
+/** Common directories where the Antigravity CLI binary may be installed */
+const ANTIGRAVITY_SEARCH_DIRS = [
+  join(homedir(), '.local', 'bin'),
+  join(homedir(), '.antigravity', 'bin'),
+  '/usr/local/bin',
+  join(homedir(), 'bin'),
+];
+
+/** Cached directory containing the agy binary (empty string = searched but not found) */
+let _antigravityDir: string | null = null;
+
+/**
+ * Finds the directory containing the `agy` binary.
+ * Checks `which agy` first, then falls back to common install locations.
+ *
+ * @returns Directory path, or null if not found
+ */
+export function resolveAntigravityDir(): string | null {
+  if (_antigravityDir !== null) return _antigravityDir || null;
+
+  try {
+    const result = execSync('which agy', {
+      encoding: 'utf-8',
+      timeout: EXEC_TIMEOUT_MS,
+    }).trim();
+    if (result && existsSync(result)) {
+      _antigravityDir = dirname(result);
+      return _antigravityDir;
+    }
+  } catch {
+    // agy not in PATH, will check common locations
+  }
+
+  for (const dir of ANTIGRAVITY_SEARCH_DIRS) {
+    if (existsSync(join(dir, 'agy'))) {
+      _antigravityDir = dir;
+      return _antigravityDir;
+    }
+  }
+
+  _antigravityDir = '';
+  return null;
+}
+
+/**
+ * Check if the Antigravity CLI is available on the system.
+ */
+export function isAntigravityAvailable(): boolean {
+  return resolveAntigravityDir() !== null;
+}

src/utils/claude-cli-resolver.ts

@@ -26,6 +26,15 @@ const CLAUDE_SEARCH_DIRS = [
 /** Cached directory containing the claude binary (empty string = searched but not found) */
 let _claudeDir: string | null = null;
 
+/**
+ * Returns true if the Claude CLI binary can be located (via `which` or one of
+ * the common install directories). Mirrors `isGeminiAvailable`/`isOpenCodeAvailable`/
+ * `isCodexAvailable` in the sibling resolvers.
+ */
+export function isClaudeAvailable(): boolean {
+  return findClaudeDir() !== null;
+}
+
 /**
  * Finds the directory containing the `claude` binary.
  * Checks `which claude` first, then falls back to common install locations.
@@ -59,6 +68,21 @@ export function findClaudeDir(): string | null {
   return null;
 }
 
+/**
+ * Returns an absolute path to the `claude` binary, falling back to the bare
+ * name `'claude'` when it cannot be located (so PATH resolution still gets a
+ * chance).
+ *
+ * Preferred over passing `'claude'` to `pty.spawn()`: a PTY child resolves the
+ * command against the environment it is handed, and an install that lives in
+ * `~/.local/bin` or `~/.claude/local` is frequently absent from the PATH the
+ * server process inherited (issue #6).
+ */
+export function getClaudeBinaryPath(): string {
+  const dir = findClaudeDir();
+  return dir ? join(dir, 'claude') : 'claude';
+}
+
 /** Cached augmented PATH string */
 let _augmentedPath: string | null = null;
 

src/utils/cloudflared-resolver.ts

@@ -0,0 +1,65 @@
+/**
+ * @fileoverview Resolve the `cloudflared` binary across common install paths.
+ *
+ * Mirrors the CLI resolvers (gemini-cli-resolver.ts et al), for the same reason
+ * they exist: the welcome screen should not offer a button whose only possible
+ * outcome is an error toast.
+ *
+ * The search list is deliberately the SAME one `TunnelManager.resolveCloudflared()`
+ * has always used, and that method now delegates here so the two can never drift.
+ * The difference is the fallback: this module answers "is it installed?" honestly
+ * with null, while the tunnel manager keeps falling back to the bare name so a
+ * cloudflared that only exists somewhere on the tunnel process's PATH still
+ * starts. A stricter answer there would turn a working tunnel into a refusal.
+ *
+ * @module utils/cloudflared-resolver
+ */
+
+import { execSync } from 'node:child_process';
+import { existsSync } from 'node:fs';
+import { join } from 'node:path';
+import { homedir } from 'node:os';
+import { EXEC_TIMEOUT_MS } from '../config/exec-timeout.js';
+
+/** Common directories where the cloudflared binary may be installed */
+const CLOUDFLARED_SEARCH_DIRS = [join(homedir(), '.local', 'bin'), '/usr/local/bin'];
+
+/** Cached path to the cloudflared binary (empty string = searched but not found) */
+let _cloudflaredPath: string | null = null;
+
+/**
+ * Finds the `cloudflared` binary.
+ *
+ * @returns Absolute path, or null if not found
+ */
+export function resolveCloudflaredPath(): string | null {
+  if (_cloudflaredPath !== null) return _cloudflaredPath || null;
+
+  for (const dir of CLOUDFLARED_SEARCH_DIRS) {
+    const candidate = join(dir, 'cloudflared');
+    if (existsSync(candidate)) {
+      _cloudflaredPath = candidate;
+      return candidate;
+    }
+  }
+
+  try {
+    const result = execSync('which cloudflared', { encoding: 'utf-8', timeout: EXEC_TIMEOUT_MS }).trim();
+    if (result && existsSync(result)) {
+      _cloudflaredPath = result;
+      return result;
+    }
+  } catch {
+    // Not on PATH either.
+  }
+
+  _cloudflaredPath = ''; // mark as searched, not found
+  return null;
+}
+
+/**
+ * Check if cloudflared is available on the system.
+ */
+export function isCloudflaredAvailable(): boolean {
+  return resolveCloudflaredPath() !== null;
+}

src/utils/index.ts

@@ -26,7 +26,10 @@ export { isSafePushEndpoint } from './push-endpoint-validation.js';
 export { stringSimilarity, fuzzyPhraseMatch, todoContentHash } from './string-similarity.js';
 export { assertNever } from './type-safety.js';
 export { wrapWithNice } from './nice-wrapper.js';
-export { findClaudeDir, getAugmentedPath, getClaudeCliVersion } from './claude-cli-resolver.js';
+export { resolveLocalShell, loginShellArgs } from './shell-resolver.js';
+export { findClaudeDir, getAugmentedPath, getClaudeCliVersion, getClaudeBinaryPath } from './claude-cli-resolver.js';
+export { spawnPtyWithHelperRepair } from './node-pty-repair.js';
 export { resolveOpenCodeDir } from './opencode-cli-resolver.js';
 export { resolveCodexDir, isCodexAvailable } from './codex-cli-resolver.js';
 export { resolveGeminiDir, isGeminiAvailable } from './gemini-cli-resolver.js';
+export { resolveAntigravityDir, isAntigravityAvailable } from './antigravity-cli-resolver.js';

src/utils/node-pty-repair.ts

@@ -0,0 +1,153 @@
+/**
+ * @fileoverview Runtime self-heal for node-pty's macOS `spawn-helper`.
+ *
+ * node-pty@1.1.0 ships its macOS prebuilt helper as
+ * `prebuilds/darwin-<arch>/spawn-helper` with mode 0644 (no execute bit). On
+ * macOS every PTY is launched through that helper via posix_spawnp, so a
+ * non-executable helper turns every session start into
+ * `Error: posix_spawnp failed.` (issues #6 and #204). The bug is macOS-only:
+ * `spawn-helper` is an `OS=="mac"` gyp target and pty.cc only spawns it under
+ * `#if defined(__APPLE__)`, and node-pty ships no Linux prebuild, so Linux always
+ * compiles a correctly-permissioned helper from source.
+ *
+ * `scripts/fix-node-pty.mjs` fixes this at install time. This module is the
+ * safety net for installs that are already broken: the first PTY spawn that
+ * fails this way is repaired and retried in-process, so the user never sees a
+ * dead session. If the retry still fails, the thrown error carries the manual
+ * repair command instead of a bare "posix_spawnp failed".
+ *
+ * @module utils/node-pty-repair
+ */
+
+import { chmodSync, existsSync, readdirSync, statSync } from 'node:fs';
+import { createRequire } from 'node:module';
+import { dirname, join } from 'node:path';
+
+const require = createRequire(import.meta.url);
+
+/** The one-line fix appended to errors we could not repair automatically. */
+export const SPAWN_HELPER_FIX_HINT =
+  'node-pty cannot execute its spawn-helper. Repair it with: npm run fix:node-pty ' +
+  '(or: chmod +x node_modules/node-pty/prebuilds/*/spawn-helper)';
+
+/** Set once a repair has been attempted, so a genuinely broken install cannot chmod-storm. */
+let repairAttempted = false;
+
+/**
+ * True when an error is node-pty failing to launch its spawn-helper.
+ *
+ * The native throw site is `throw Napi::Error::New(napiEnv, "posix_spawnp failed.")`
+ * in pty.cc, reached only on Apple platforms.
+ */
+export function isSpawnHelperFailure(err: unknown): boolean {
+  const message = err instanceof Error ? err.message : String(err ?? '');
+  return /posix_spawnp|spawn-helper/i.test(message);
+}
+
+/** Locates the installed node-pty package root, or null when it can't be resolved. */
+export function findNodePtyDir(): string | null {
+  // node-pty declares no "exports" map, so the package.json subpath resolves and
+  // lands on the package root. require.resolve('node-pty') would return
+  // <pkg>/lib/index.js, one level deeper than callers need.
+  try {
+    return dirname(require.resolve('node-pty/package.json'));
+  } catch {
+    /* fall through */
+  }
+  try {
+    return join(dirname(require.resolve('node-pty')), '..');
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * Lists every `spawn-helper` present in a node-pty install.
+ *
+ * node-pty's loader checks `build/Release`, `build/Debug`, then
+ * `prebuilds/<platform>-<arch>`, and takes the helper from whichever directory
+ * the native module loaded out of, so every copy has to be executable, not just
+ * the one this machine happens to use.
+ */
+export function listSpawnHelpers(ptyDir: string): string[] {
+  const dirs = [join(ptyDir, 'build', 'Release'), join(ptyDir, 'build', 'Debug')];
+
+  const prebuilds = join(ptyDir, 'prebuilds');
+  if (existsSync(prebuilds)) {
+    try {
+      for (const entry of readdirSync(prebuilds, { withFileTypes: true })) {
+        if (entry.isDirectory()) dirs.push(join(prebuilds, entry.name));
+      }
+    } catch {
+      /* unreadable prebuilds dir: nothing to repair there */
+    }
+  }
+
+  return dirs.map((d) => join(d, 'spawn-helper')).filter((p) => existsSync(p));
+}
+
+/**
+ * Adds the execute bit to every `spawn-helper` missing it.
+ *
+ * @param ptyDir - node-pty package root; resolved automatically when omitted.
+ * @returns Paths actually changed (empty when nothing needed repair, or node-pty
+ *   is missing, or the files are not writable).
+ */
+export function repairSpawnHelperPermissions(ptyDir?: string): string[] {
+  const dir = ptyDir ?? findNodePtyDir();
+  if (!dir) return [];
+
+  const repaired: string[] = [];
+  for (const helper of listSpawnHelpers(dir)) {
+    try {
+      const mode = statSync(helper).mode & 0o777;
+      if ((mode & 0o111) === 0o111) continue;
+      chmodSync(helper, mode | 0o755);
+      repaired.push(helper);
+    } catch {
+      // Read-only install (or not ours to chmod): fall through to the hint.
+    }
+  }
+  return repaired;
+}
+
+/** Wraps an error so the message carries the actionable repair command. */
+function withFixHint(err: unknown): Error {
+  const message = err instanceof Error ? err.message : String(err);
+  return new Error(`${message}. ${SPAWN_HELPER_FIX_HINT}`, { cause: err });
+}
+
+/**
+ * Runs a `pty.spawn()` call, repairing a non-executable spawn-helper and
+ * retrying once if that is why it failed.
+ *
+ * Any unrelated spawn error is rethrown untouched, so this stays invisible on
+ * every platform but a broken macOS install.
+ *
+ * @param spawn - The `pty.spawn(...)` call to run.
+ * @param ptyDir - node-pty package root; resolved automatically when omitted.
+ */
+export function spawnPtyWithHelperRepair<T>(spawn: () => T, ptyDir?: string): T {
+  try {
+    return spawn();
+  } catch (err) {
+    if (!isSpawnHelperFailure(err)) throw err;
+    if (repairAttempted) throw withFixHint(err);
+
+    repairAttempted = true;
+    const repaired = repairSpawnHelperPermissions(ptyDir);
+    if (repaired.length === 0) throw withFixHint(err);
+
+    console.warn(`[node-pty] spawn-helper was not executable, repaired ${repaired.join(', ')} and retrying`);
+    try {
+      return spawn();
+    } catch (retryErr) {
+      throw withFixHint(retryErr);
+    }
+  }
+}
+
+/** Test seam: forget that a repair was already attempted in this process. */
+export function resetSpawnHelperRepairState(): void {
+  repairAttempted = false;
+}

src/utils/regex-patterns.ts

@@ -60,7 +60,7 @@ export function stripAnsi(text: string): string {
  */
 export const SPINNER_PATTERN = /[⠋⠙⠹⠸⠼⠴⠦⠧]/;
 
-export const SAFE_PATH_PATTERN = /^[a-zA-Z0-9_/\-. ~]+$/;
+export const SAFE_PATH_PATTERN = /^[\p{L}\p{N}_/\-. ~]+$/u;
 
 /**
  * Execute a global regex pattern against data, calling the callback for each match.

src/utils/shell-resolver.ts

@@ -0,0 +1,111 @@
+/**
+ * @fileoverview Resolve a real, launchable login shell for `mode: 'shell'` sessions.
+ *
+ * The tmux pane command for a local shell session used to be the literal string
+ * `$SHELL`. That string is embedded in the `bash -c "…"` argument of the
+ * `respawn-pane` line, which `execSync` hands to `/bin/sh -c` — so `$SHELL` was
+ * expanded by the SERVER process's shell (not the pane's), against the SERVER
+ * process's env. Containers and system-level systemd units do not set `SHELL`,
+ * so the expansion produced an empty string and the pane command ended in a
+ * dangling `&&`:
+ *
+ *   bash -c "cd \"/case\" && ulimit … && export … && "
+ *   -> bash: -c: line 1: syntax error: unexpected end of file
+ *
+ * The pane then died instantly (status 2) while tmux creation itself reported
+ * success, which is exactly what issue #208 saw. Resolving the shell HERE, in
+ * Node, removes the shell-expansion layer entirely and guarantees a non-empty
+ * absolute path.
+ *
+ * @module utils/shell-resolver
+ */
+
+import { accessSync, constants } from 'node:fs';
+import { userInfo } from 'node:os';
+
+/** Last-resort shells, in preference order. `/bin/sh` exists on every POSIX host. */
+const FALLBACK_SHELLS = ['/bin/bash', '/bin/zsh', '/bin/sh'];
+
+/**
+ * Shells that exist and are executable but immediately exit — a service account's
+ * passwd entry commonly points at one, which would look identical to the crash
+ * this module exists to prevent.
+ */
+const NON_INTERACTIVE_SHELLS = new Set(['nologin', 'false', 'true', 'sync']);
+
+/**
+ * Shells verified to accept BOTH `-i` and `-l`. Deliberately an allowlist, not a
+ * blocklist: a shell that rejects an unknown flag exits immediately, which is the
+ * dead-pane-on-arrival failure this module exists to prevent (#208). The passwd
+ * entry is user data and can name anything — nushell, elvish, and xonsh all take
+ * neither flag in this form, so they get a bare launch instead of a dead tab.
+ *
+ * csh/tcsh are excluded on purpose: tcsh honors `-l` only when it is the ONLY
+ * flag, so `-i -l` would silently not be a login shell there anyway.
+ */
+const LOGIN_FLAG_SHELLS = new Set(['sh', 'bash', 'dash', 'ash', 'zsh', 'ksh', 'ksh93', 'mksh', 'pdksh', 'fish']);
+
+function isUsableShell(candidate: string): boolean {
+  if (!candidate.startsWith('/')) return false;
+  const base = candidate.slice(candidate.lastIndexOf('/') + 1);
+  if (NON_INTERACTIVE_SHELLS.has(base)) return false;
+  try {
+    accessSync(candidate, constants.X_OK);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Resolve an absolute path to an interactive shell, preferring the user's own.
+ *
+ * Order: `$SHELL` -> the passwd entry -> `/bin/bash` -> `/bin/zsh` -> `/bin/sh`.
+ * Every candidate must be an absolute path to an executable that is not a
+ * nologin-style stub. Always returns a non-empty string.
+ */
+export function resolveLocalShell(): string {
+  const candidates: string[] = [];
+
+  const envShell = process.env.SHELL?.trim();
+  if (envShell) candidates.push(envShell);
+
+  try {
+    // Throws when the uid has no /etc/passwd entry (common for `--user` containers).
+    const passwdShell = userInfo().shell?.trim();
+    if (passwdShell) candidates.push(passwdShell);
+  } catch {
+    /* no passwd entry — fall through to the static fallbacks */
+  }
+
+  candidates.push(...FALLBACK_SHELLS);
+
+  for (const candidate of candidates) {
+    if (isUsableShell(candidate)) return candidate;
+  }
+
+  // Nothing was verifiable (exotic/read-restricted image). /bin/sh is still the
+  // best guess and is far better than emitting an empty command.
+  return '/bin/sh';
+}
+
+/**
+ * Flags that make `shellPath` a login shell, or `''` when it takes none we trust.
+ *
+ * A tmux pane already hands the shell a tty, so it is interactive with or without
+ * `-i` (verified: `$-` contains `i` for a bare `/bin/bash` in a pane, which is why
+ * `~/.bashrc` has always been sourced). The flag that actually changes anything is
+ * `-l`: it makes the pane a LOGIN shell, matching what tmux itself does when it
+ * spawns a pane with no `default-command`, and picking up the `/etc/profile` and
+ * `/etc/profile.d/*` PATH entries that a systemd-spawned server never sourced.
+ *
+ * `-i` is kept alongside it because for bash the two select different files —
+ * login reads `~/.bash_profile`, interactive-non-login reads `~/.bashrc` — and
+ * asking for both is the closest thing to "the shell the user actually gets".
+ *
+ * Returns a string ready to append to an already-escaped shell path.
+ */
+export function loginShellArgs(shellPath: string): string {
+  const base = shellPath.slice(shellPath.lastIndexOf('/') + 1);
+  return LOGIN_FLAG_SHELLS.has(base) ? ' -i -l' : '';
+}

src/web/admin-audit.ts

@@ -0,0 +1,28 @@
+/**
+ * @fileoverview Append-only admin audit log (~/.codeman/admin-audit.jsonl).
+ *
+ * Every user-management action (create/patch/reset/delete/logout/assign) writes one
+ * JSON line: timestamp, acting admin, action, target, request IP. Same idiom as
+ * session-lifecycle.jsonl. Best-effort: a write failure never blocks the action.
+ */
+
+import fs from 'node:fs/promises';
+import { dataPath } from '../config/instance.js';
+
+export interface AdminAuditEntry {
+  ts: number;
+  admin: string;
+  action: string;
+  target?: string;
+  ip?: string;
+  detail?: Record<string, unknown>;
+}
+
+export async function appendAdminAudit(entry: Omit<AdminAuditEntry, 'ts'>): Promise<void> {
+  try {
+    const line = JSON.stringify({ ts: Date.now(), ...entry }) + '\n';
+    await fs.appendFile(dataPath('admin-audit.jsonl'), line, { mode: 0o600 });
+  } catch {
+    /* best-effort audit; never block the action */
+  }
+}

src/web/middleware/auth.ts

@@ -8,7 +8,7 @@
  * - CORS (localhost only)
  */
 
-import type { FastifyInstance, FastifyReply } from 'fastify';
+import type { FastifyInstance, FastifyReply, FastifyRequest } from 'fastify';
 import { randomBytes, timingSafeEqual } from 'node:crypto';
 import { StaleExpirationMap } from '../../utils/index.js';
 import type { AuthSessionRecord } from '../ports/auth-port.js';
@@ -20,6 +20,19 @@ import {
   AUTH_FAILURE_WINDOW_MS,
 } from '../../config/auth-config.js';
 import { getHookSecret, HOOK_SECRET_HEADER } from '../../config/hook-secret.js';
+import { isMultiUserMode } from '../../config/multiuser.js';
+import { findUser, setPassword, touchLastLogin, verifyPassword } from '../../user-store.js';
+import { webviewCapabilities } from '../../webview-capabilities.js';
+import { capabilityFromProxyPath, capabilityFromReferer } from '../webview-proxy.js';
+import { ApiErrorCode, createErrorResponse, type AuthUser } from '../../types.js';
+
+// Request-scoped identity (multi-user). Single-user leaves it undefined and the
+// ownership helpers default to a synthetic admin (see route-helpers).
+declare module 'fastify' {
+  interface FastifyRequest {
+    authUser?: AuthUser;
+  }
+}
 
 // Auth session cookie name
 export const AUTH_COOKIE_NAME = 'codeman_session';
@@ -30,6 +43,162 @@ interface AuthState {
   authFailures: StaleExpirationMap<string, number> | null;
   qrAuthFailures: StaleExpirationMap<string, number> | null;
   hookSecretFailures: StaleExpirationMap<string, number> | null;
+  /** Per-username Basic-auth failure bucket (multi-user only). */
+  userFailures: StaleExpirationMap<string, number> | null;
+}
+
+/** Rate-limit response for a client that exceeded the failure cap. */
+function sendAuthRateLimit(reply: FastifyReply, failures: StaleExpirationMap<string, number>, key: string): void {
+  const remainingMs = failures.getRemainingTtl(key) ?? AUTH_FAILURE_WINDOW_MS;
+  const retryAfterSeconds = Math.max(1, Math.ceil(remainingMs / 1000));
+  reply.header('Retry-After', String(retryAfterSeconds));
+  reply.code(429).send('Too Many Requests — try again later');
+}
+
+/** Parse a `Basic base64(user:pass)` header into its parts, or null if malformed. */
+function parseBasicAuth(header?: string): { username: string; password: string } | null {
+  if (!header || !header.startsWith('Basic ')) return null;
+  try {
+    const decoded = Buffer.from(header.slice(6), 'base64').toString('utf-8');
+    const idx = decoded.indexOf(':');
+    if (idx < 0) return null;
+    return { username: decoded.slice(0, idx), password: decoded.slice(idx + 1) };
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * The `/api/hook-event` + `/api/status-telemetry` localhost bypass, shared by the
+ * single-user and multi-user auth hooks so the security-critical logic has ONE
+ * source of truth. Returns:
+ *  - 'bypass'   : loopback + valid hook secret; the caller should allow the request
+ *  - 'rejected' : a reply was already sent (wrong secret rate-limited / 401)
+ *  - 'continue' : not a hook request (or non-loopback); fall through to normal auth
+ *
+ * COD-91: the shared hook secret is required UNCONDITIONALLY on the loopback bypass
+ * (a user's own loopback reverse proxy is indistinguishable from a real local hook).
+ */
+function checkHookSecretBypass(
+  req: FastifyRequest,
+  reply: FastifyReply,
+  hookSecretFailures: StaleExpirationMap<string, number>
+): 'bypass' | 'rejected' | 'continue' {
+  if ((req.url === '/api/hook-event' || req.url === '/api/status-telemetry') && req.method === 'POST') {
+    const ip = req.ip;
+    const isLoopback = ip === '127.0.0.1' || ip === '::1' || ip === '::ffff:127.0.0.1';
+    if (isLoopback) {
+      const presented = Buffer.from(req.headers[HOOK_SECRET_HEADER.toLowerCase()]?.toString() ?? '');
+      const expected = Buffer.from(getHookSecret());
+      if (presented.length === expected.length && timingSafeEqual(presented, expected)) {
+        return 'bypass';
+      }
+      const hookIp = req.ip;
+      const hookFailures = hookSecretFailures.get(hookIp) ?? 0;
+      if (hookFailures >= AUTH_FAILURE_MAX) {
+        sendAuthRateLimit(reply, hookSecretFailures, hookIp);
+        return 'rejected';
+      }
+      hookSecretFailures.set(hookIp, hookFailures + 1);
+      reply.code(401).send('Unauthorized: hook secret required');
+      return 'rejected';
+    }
+    // Non-localhost hook requests fall through to normal auth
+  }
+  return 'continue';
+}
+
+/**
+ * Requests that a `mustChangePassword` user may still reach: the identity probe,
+ * the password-change endpoint, and any non-API path (static assets / index.html,
+ * so the browser can load the app and render the change-password modal).
+ */
+function isPasswordChangeExempt(req: FastifyRequest): boolean {
+  const url = (req.url ?? '').split('?')[0];
+  if (url === '/api/me' || url === '/api/me/password') return true;
+  // Security: the WebSocket terminal (/ws/...) is a functional channel, not a static
+  // asset, so it must NOT be exempt, or a locked user keeps a working terminal.
+  if (url.startsWith('/ws/')) return false;
+  return !url.startsWith('/api/');
+}
+
+/**
+ * Whether this request carries a VALID web-tab proxy capability.
+ *
+ * Requests under `/webview/<cap>/` cannot authenticate the normal way. The iframe
+ * rendering a dashboard is sandboxed without `allow-same-origin`, so it runs in an
+ * opaque origin: every request it makes is cross-site, meaning the `SameSite=lax`
+ * `codeman_session` cookie is never attached, and non-GET requests and WebSocket
+ * upgrades arrive with `Origin: null`. Both the cookie check and the CSRF Origin
+ * guard would therefore reject a perfectly legitimate dashboard asset load.
+ *
+ * The capability in the path is the credential instead: 192 bits of entropy, held
+ * in memory only (a restart invalidates it), rolling TTL, bound to the user who
+ * minted it through an already-authenticated `POST /api/webviews/:id/open`, and
+ * granting nothing but "relay bytes to this one saved URL".
+ *
+ * The exemption is deliberately narrow: it requires the capability to RESOLVE, so
+ * a bare `/webview/anything` reaches nothing, and a `/webviewfoo` path does not
+ * match the prefix at all. The Host allowlist is NOT bypassed, so DNS-rebinding
+ * protection still applies to these requests.
+ */
+function hasValidWebviewCapability(req: FastifyRequest): boolean {
+  const url = (req.url ?? '').split('?')[0];
+
+  const fromPath = capabilityFromProxyPath(url);
+  if (fromPath) return webviewCapabilities.resolve(fromPath) !== undefined;
+
+  // Referer form: a dashboard subresource requested with a ROOT-ABSOLUTE URL, which
+  // lands on Codeman's root and is relayed by the 404 fallback. Without this the
+  // asset would be rejected here, before the fallback ever runs.
+  //
+  // This is the only exemption decided by a header the request itself supplies, so
+  // it is fenced in hard: safe methods only, and never for Codeman's own functional
+  // surfaces. Without those fences a page could present a webview Referer and skip
+  // auth on /api. It is not a privilege escalation even so, holding a live
+  // capability already implies an authenticated `POST /api/webviews/:id/open`, but
+  // the exemption should stay no wider than the problem it solves.
+  if (req.method !== 'GET' && req.method !== 'HEAD') return false;
+  if (url.startsWith('/ws/') || url.startsWith('/q/')) return false;
+  // Anything that resolves to a REAL Codeman route is refused, which is the fence
+  // that keeps this from being an auth bypass. `/api/` used to be refused by prefix
+  // instead, but dashboards legitimately serve assets from their own `/api/...`
+  // namespace (`<img src="/api/hero?slug=x">`), and those requests were the one
+  // class the 404 relay could never rescue. See matchesRegisteredRoute.
+  if (matchesRegisteredRoute(req, url)) return false;
+
+  const fromReferer = capabilityFromReferer(typeof req.headers.referer === 'string' ? req.headers.referer : undefined);
+  return !!fromReferer && webviewCapabilities.resolve(fromReferer) !== undefined;
+}
+
+/**
+ * Whether `url` resolves to a route Codeman actually registered.
+ *
+ * `hasRoute()` is the wrong tool: it matches the registered PATTERN literally, so
+ * `/api/sessions/abc` reports false against a registered `/api/sessions/:id` and
+ * would hand out an exemption on a live API route. `findRoute()` performs the real
+ * radix-tree lookup and fills in `params`, which is what this needs.
+ *
+ * The one complication is `@fastify/static`, mounted at `/`, which registers a
+ * root-level catch-all that matches EVERY path. A match on that means "no real
+ * route, this is heading for the 404 handler", and it is distinguishable because a
+ * root catch-all is the only route whose `*` param comes back equal to the entire
+ * request path. `test/webview-auth-exemption.test.ts` pins both halves of that.
+ *
+ * Fails CLOSED: anything unexpected counts as a real route, which merely denies the
+ * exemption and restores the previous behavior.
+ */
+function matchesRegisteredRoute(req: FastifyRequest, url: string): boolean {
+  try {
+    const found = req.server.findRoute({ method: req.method as 'GET' | 'HEAD', url });
+    if (!found) return false;
+    const params = found.params ?? {};
+    const keys = Object.keys(params);
+    const isRootCatchAll = keys.length === 1 && keys[0] === '*' && `/${params['*']}` === url;
+    return !isRootCatchAll;
+  } catch {
+    return true;
+  }
 }
 
 /**
@@ -47,13 +216,20 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
     authFailures: null,
     qrAuthFailures: null,
     hookSecretFailures: null,
+    userFailures: null,
   };
 
-  const authPassword = process.env.CODEMAN_PASSWORD;
-  if (!authPassword) return state;
+  // Always declare req.authUser so downstream reads are safe (single-user leaves it
+  // undefined; the ownership helpers then default to a synthetic admin).
+  if (!app.hasRequestDecorator('authUser')) app.decorateRequest('authUser', undefined);
 
-  const authUsername = process.env.CODEMAN_USERNAME || 'admin';
-  const expectedHeader = 'Basic ' + Buffer.from(`${authUsername}:${authPassword}`).toString('base64');
+  const multiUser = isMultiUserMode();
+  const authPassword = process.env.CODEMAN_PASSWORD;
+
+  // No auth at all: single-user with no password (byte-identical to legacy). In
+  // multi-user mode auth is ALWAYS active (users authenticate individually), even
+  // without CODEMAN_PASSWORD.
+  if (!multiUser && !authPassword) return state;
 
   // Session token store — active sessions extend TTL on access
   state.authSessions = new StaleExpirationMap<string, AuthSessionRecord>({
@@ -87,57 +263,28 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
   const authFailures = state.authFailures;
   const hookSecretFailures = state.hookSecretFailures;
 
-  function sendAuthRateLimit(
-    reply: FastifyReply,
-    clientIp: string,
-    failures: StaleExpirationMap<string, number> = authFailures
-  ): void {
-    const remainingMs = failures.getRemainingTtl(clientIp) ?? AUTH_FAILURE_WINDOW_MS;
-    const retryAfterSeconds = Math.max(1, Math.ceil(remainingMs / 1000));
-    reply.header('Retry-After', String(retryAfterSeconds));
-    reply.code(429).send('Too Many Requests — try again later');
+  if (multiUser) {
+    // Per-username failure bucket: a botnet can't brute-force one account across
+    // many IPs, and one user behind a NAT can't lock out everyone else.
+    state.userFailures = new StaleExpirationMap<string, number>({
+      ttlMs: AUTH_FAILURE_WINDOW_MS,
+      refreshOnGet: false,
+    });
+    registerMultiUserAuthHook(app, https, authSessions, authFailures, hookSecretFailures, state.userFailures);
+    return state;
   }
 
+  // ── Single-user Basic Auth (unchanged behavior; CODEMAN_PASSWORD required) ──
+  const authUsername = process.env.CODEMAN_USERNAME || 'admin';
+  const expectedHeader = 'Basic ' + Buffer.from(`${authUsername}:${authPassword}`).toString('base64');
+
   app.addHook('onRequest', (req, reply, done) => {
-    // Hook events + statusline telemetry come from local Claude Code (curl from
-    // localhost) — no Basic-Auth credentials available. Validated downstream by
-    // HookEventSchema / StatusTelemetrySchema. Same loopback+hook-secret gate.
-    //
-    // COD-54: the bare localhost bypass is unsafe while a tunnel is running, because
-    // `cloudflared --url http://127.0.0.1:port` proxies internet traffic INTO the
-    // loopback origin, so a tunneled request arrives with req.ip === 127.0.0.1 and
-    // would pass. COD-91: require the shared hook secret on the loopback bypass
-    // UNCONDITIONALLY (not just while the managed tunnel is up). Codeman can't detect
-    // a user's own loopback reverse proxy (their own `cloudflared --url`, `tailscale
-    // serve`, nginx → 127.0.0.1), so tunnel-gating left that path with the unsafe plain
-    // bypass. Managed-session hooks always present the secret (X-Codeman-Hook-Secret,
-    // from $CODEMAN_HOOK_SECRET_FILE — generated for every instance), so requiring it
-    // always closes the gap without breaking the legitimate hook channel.
-    if ((req.url === '/api/hook-event' || req.url === '/api/status-telemetry') && req.method === 'POST') {
-      const ip = req.ip;
-      const isLoopback = ip === '127.0.0.1' || ip === '::1' || ip === '::ffff:127.0.0.1';
-      if (isLoopback) {
-        // Always require the shared secret (constant-time compare).
-        const presented = Buffer.from(req.headers[HOOK_SECRET_HEADER.toLowerCase()]?.toString() ?? '');
-        const expected = Buffer.from(getHookSecret());
-        if (presented.length === expected.length && timingSafeEqual(presented, expected)) {
-          done();
-          return;
-        }
-        // Wrong/absent secret — rate-limit per IP in the DEDICATED hook bucket
-        // (never authFailures, which would lock out the login path).
-        const hookIp = req.ip;
-        const hookFailures = hookSecretFailures.get(hookIp) ?? 0;
-        if (hookFailures >= AUTH_FAILURE_MAX) {
-          sendAuthRateLimit(reply, hookIp, hookSecretFailures);
-          return;
-        }
-        hookSecretFailures.set(hookIp, hookFailures + 1);
-        reply.code(401).send('Unauthorized: hook secret required');
-        return;
-      }
-      // Non-localhost hook requests fall through to normal auth
+    const bypass = checkHookSecretBypass(req, reply, hookSecretFailures);
+    if (bypass === 'bypass') {
+      done();
+      return;
     }
+    if (bypass === 'rejected') return;
 
     // QR auth path — handled by the route itself (token validation + rate limiting)
     if (req.url?.startsWith('/q/')) {
@@ -145,6 +292,12 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
       return;
     }
 
+    // Web-tab proxy, authenticated by the capability in the path, not the cookie.
+    if (hasValidWebviewCapability(req)) {
+      done();
+      return;
+    }
+
     const clientIp = req.ip;
 
     // Check session cookie first (avoids re-sending credentials on every request)
@@ -153,10 +306,6 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
     if (sessionToken && authSessions.get(sessionToken) !== undefined) {
       // Sliding cookie: re-issue on every authenticated request so the browser
       // cookie lifetime tracks the server-side sliding TTL (refreshOnGet above).
-      // Without this the cookie has a fixed lifetime from login; the browser
-      // drops it mid-use, the next request arrives cookie-less and falls through
-      // to Basic Auth — popping the native username/password dialog, which reads
-      // as a random logout while actively working.
       reply.setCookie(AUTH_COOKIE_NAME, sessionToken, {
         httpOnly: true,
         secure: https,
@@ -206,7 +355,7 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
     // Rate limit only requests that failed to authenticate on this attempt.
     const failures = authFailures.get(clientIp) ?? 0;
     if (failures >= AUTH_FAILURE_MAX) {
-      sendAuthRateLimit(reply, clientIp);
+      sendAuthRateLimit(reply, authFailures, clientIp);
       return;
     }
 
@@ -220,6 +369,170 @@ export function registerAuthMiddleware(app: FastifyInstance, https: boolean): Au
   return state;
 }
 
+/**
+ * Multi-user auth hook (async, because password verification runs scrypt). Verifies
+ * `username:password` against the user store, mints an identity-carrying cookie,
+ * decorates `req.authUser`, enforces the per-IP + per-username rate limits, and the
+ * `mustChangePassword` lockbox. The single-user hook above is left untouched.
+ */
+function registerMultiUserAuthHook(
+  app: FastifyInstance,
+  https: boolean,
+  authSessions: StaleExpirationMap<string, AuthSessionRecord>,
+  authFailures: StaleExpirationMap<string, number>,
+  hookSecretFailures: StaleExpirationMap<string, number>,
+  userFailures: StaleExpirationMap<string, number>
+): void {
+  const setSessionCookie = (reply: FastifyReply, token: string) =>
+    reply.setCookie(AUTH_COOKIE_NAME, token, {
+      httpOnly: true,
+      secure: https,
+      sameSite: 'lax',
+      maxAge: AUTH_SESSION_TTL_MS / 1000,
+      path: '/',
+    });
+
+  // Evict the oldest cookie session of the SAME user first (so one user logging in
+  // 100 times cannot flush everyone else's sessions), falling back to global-oldest.
+  const evictForCapacity = (username: string) => {
+    let userKey: string | undefined;
+    let userTs = Infinity;
+    let globalKey: string | undefined;
+    let globalTs = Infinity;
+    for (const [k, v] of authSessions) {
+      if (v.createdAt < globalTs) {
+        globalTs = v.createdAt;
+        globalKey = k;
+      }
+      if (v.username === username && v.createdAt < userTs) {
+        userTs = v.createdAt;
+        userKey = k;
+      }
+    }
+    const key = userKey ?? globalKey;
+    if (key !== undefined) authSessions.delete(key);
+  };
+
+  const enforcePasswordChange = (req: FastifyRequest, reply: FastifyReply, mustChange: boolean): boolean => {
+    if (mustChange && !isPasswordChangeExempt(req)) {
+      reply.code(403).send(createErrorResponse(ApiErrorCode.PASSWORD_CHANGE_REQUIRED));
+      return true;
+    }
+    return false;
+  };
+
+  app.addHook('onRequest', async (req, reply) => {
+    const bypass = checkHookSecretBypass(req, reply, hookSecretFailures);
+    if (bypass === 'bypass' || bypass === 'rejected') return;
+
+    // QR redemption path — handled by the route itself.
+    if (req.url?.startsWith('/q/')) return;
+
+    // Web-tab proxy, authenticated by the capability in the path, not the cookie.
+    // `req.authUser` stays undefined here on purpose: the proxy handler enforces
+    // ownership against the identity BOUND TO THE CAPABILITY, which is stricter
+    // than re-deriving it from a request that carries no credentials.
+    if (hasValidWebviewCapability(req)) return;
+
+    const clientIp = req.ip;
+
+    // 1. Cookie session (carries identity + mustChangePassword snapshot).
+    const sessionToken = req.cookies[AUTH_COOKIE_NAME];
+    const record = sessionToken ? authSessions.get(sessionToken) : undefined;
+    if (record && record.username) {
+      // Security: re-validate the cookie identity against the store on every request so
+      // an out-of-band mutation the in-memory map can't see (the `codeman users` CLI,
+      // a separate process, deleting/disabling/demoting a user) takes effect promptly
+      // instead of riding the 24h cookie. findUser is cached ~1s, so this is cheap.
+      let live: Awaited<ReturnType<typeof findUser>>;
+      try {
+        live = await findUser(record.username);
+      } catch {
+        // The store is transiently unreadable/corrupt (readUsers throws on a non-ENOENT
+        // read, #23). Fall back to the cookie's snapshot for THIS request rather than
+        // 500-ing an already-authenticated client (pre-#24 behaviour); a persistently
+        // corrupt store still fails all WRITES loudly at the mutator/bootstrap layer.
+        req.authUser = { username: record.username, role: record.role ?? 'user' };
+        setSessionCookie(reply, sessionToken!);
+        enforcePasswordChange(req, reply, !!record.mustChangePassword);
+        return;
+      }
+      if (!live || live.disabled) {
+        authSessions.delete(sessionToken!);
+        reply.clearCookie(AUTH_COOKIE_NAME, { path: '/' });
+        reply.code(401).send('Unauthorized');
+        return;
+      }
+      // Trust the LIVE role/mustChangePassword, not the (possibly stale) cookie snapshot
+      // (also defends #9/#13: a CLI demotion is reflected without a revoke).
+      req.authUser = { username: live.username, role: live.role };
+      setSessionCookie(reply, sessionToken!); // sliding re-issue
+      enforcePasswordChange(req, reply, !!live.mustChangePassword);
+      return;
+    }
+
+    // 2. Basic Auth against the user store (scrypt verify).
+    // Per-IP pre-gate bounds scrypt CPU cost from one source (does NOT gate on the
+    // per-username bucket here; see below).
+    const ipFail = authFailures.get(clientIp) ?? 0;
+    if (ipFail >= AUTH_FAILURE_MAX) {
+      sendAuthRateLimit(reply, authFailures, clientIp);
+      return;
+    }
+    const creds = parseBasicAuth(req.headers.authorization);
+    if (creds) {
+      const normUser = creds.username.trim().toLowerCase();
+      // Security: VERIFY FIRST, then throttle only FAILED attempts. Consulting the
+      // per-username bucket before verifying let throwaway IPs lock out a known account
+      // (incl. admin) even with the correct password. A correct password must always
+      // win and self-heal both buckets, regardless of the username-failure count.
+      const result = await verifyPassword(creds.username, creds.password);
+      if (result) {
+        const { user, needsRehash: rehash } = result;
+        if (rehash) void setPassword(user.username, creds.password).catch(() => {});
+        void touchLastLogin(user.username).catch(() => {});
+        authFailures.delete(clientIp);
+        userFailures.delete(normUser);
+
+        const token = randomBytes(32).toString('hex');
+        if (authSessions.size >= MAX_AUTH_SESSIONS) evictForCapacity(user.username);
+        authSessions.set(token, {
+          ip: clientIp,
+          ua: req.headers['user-agent'] ?? '',
+          createdAt: Date.now(),
+          method: 'basic',
+          username: user.username,
+          role: user.role,
+          mustChangePassword: !!user.mustChangePassword,
+        });
+        req.authUser = { username: user.username, role: user.role };
+        setSessionCookie(reply, token);
+        enforcePasswordChange(req, reply, !!user.mustChangePassword);
+        return;
+      }
+      // Failed guess: count it against BOTH buckets. Once the per-username bucket
+      // reaches the cap, further FAILED attempts get 429 (throttles distributed
+      // brute-force), but this path is only reached on a wrong password, so it can
+      // never deny a correct one.
+      const uFail = (userFailures.get(normUser) ?? 0) + 1;
+      userFailures.set(normUser, uFail);
+      authFailures.set(clientIp, ipFail + 1);
+      if (uFail >= AUTH_FAILURE_MAX) {
+        sendAuthRateLimit(reply, userFailures, normUser);
+        return;
+      }
+      reply.header('WWW-Authenticate', 'Basic realm="Codeman"');
+      reply.code(401).send('Unauthorized');
+      return;
+    }
+
+    // No credentials presented: count against the per-IP bucket and challenge.
+    authFailures.set(clientIp, ipFail + 1);
+    reply.header('WWW-Authenticate', 'Basic realm="Codeman"');
+    reply.code(401).send('Unauthorized');
+  });
+}
+
 /** Methods that don't change server state and so skip the cross-site Origin check. */
 const SAFE_HTTP_METHODS = new Set(['GET', 'HEAD', 'OPTIONS']);
 
@@ -246,7 +559,17 @@ export function registerHostGuard(app: FastifyInstance, getPolicy: () => HostPol
       reply.code(403).send('Forbidden: host not allowed');
       return;
     }
-    if (!SAFE_HTTP_METHODS.has(req.method) && !isAllowedRequestOrigin(req.headers.origin, policy)) {
+    // The Host allowlist above is NEVER bypassed. The Origin (CSRF) check is,
+    // but only for a request carrying a valid web-tab capability: a sandboxed
+    // dashboard is opaque-origin, so its form posts and uploads arrive with
+    // `Origin: null`, which this guard rejects by design. The capability is the
+    // credential in that case, and it is unguessable, see
+    // hasValidWebviewCapability.
+    if (
+      !SAFE_HTTP_METHODS.has(req.method) &&
+      !isAllowedRequestOrigin(req.headers.origin, policy) &&
+      !hasValidWebviewCapability(req)
+    ) {
       reply.code(403).send('Forbidden: cross-site request blocked');
       return;
     }
@@ -301,8 +624,17 @@ export function registerSecurityHeaders(app: FastifyInstance, https: boolean): v
       }
     }
 
-    // Handle CORS preflight
-    if (req.method === 'OPTIONS') {
+    // Handle CORS preflight.
+    //
+    // EXCEPT for the web-tab proxy, which must answer its own preflight. A
+    // sandboxed dashboard iframe is opaque-origin, so it sends `Origin: null`;
+    // the CORS block above only emits headers for localhost origins, so a bare
+    // 204 from here carries no `Access-Control-Allow-Origin` and the browser
+    // rejects the preflight. Every dashboard fetch then fails with an opaque
+    // net::ERR_FAILED while the page itself renders fine (script/css/img loads
+    // are not CORS-checked). Falling through lets the proxy route reply with the
+    // right headers.
+    if (req.method === 'OPTIONS' && !hasValidWebviewCapability(req)) {
       reply.code(204).send();
       done();
       return;

src/web/ports/auth-port.ts

@@ -11,6 +11,19 @@ export interface AuthSessionRecord {
   ua: string;
   createdAt: number;
   method: 'qr' | 'basic';
+  /**
+   * Multi-user identity carried by the cookie (single-user leaves these unset).
+   * Snapshotted at mint time. Authorization-relevant admin changes (password reset,
+   * disable, delete, role change, bypass-grant change) revoke the user's sessions so
+   * a stale snapshot can't outlive the change; additionally the cookie fast-path
+   * re-reads role/disabled/mustChangePassword live from the store each request, so an
+   * out-of-band CLI mutation also takes effect promptly. See docs/multi-user-plan.md
+   * section 5.
+   */
+  username?: string;
+  role?: 'admin' | 'user';
+  /** Whether this user must change their password before other actions are allowed. */
+  mustChangePassword?: boolean;
 }
 
 export interface AuthPort {

src/web/ports/config-port.ts

@@ -18,7 +18,7 @@ export interface ConfigPort {
   getClaudeModeConfig(): Promise<{ claudeMode?: ClaudeMode; allowedTools?: string }>;
   getTerminalHistoryConfig(): Promise<TerminalHistoryConfig>;
   getDefaultClaudeMdPath(): Promise<string | undefined>;
-  getLightState(): unknown;
+  getLightState(identity?: { username: string; role: 'admin' | 'user' }): unknown;
   getLightSessionsState(): unknown[];
   startTranscriptWatcher(sessionId: string, transcriptPath: string): void;
   stopTranscriptWatcher(sessionId: string): void;

src/web/ports/infra-port.ts

@@ -23,6 +23,9 @@ export interface ScheduledRun {
   completedTasks: number;
   totalCost: number;
   logs: string[];
+  /** Multi-user owner (username) — undefined in single-user mode. Used to scope
+   * list/delete and to downgrade the spawned Session's permission mode. */
+  owner?: string;
 }
 
 export interface InfraPort {
@@ -33,6 +36,6 @@ export interface InfraPort {
   readonly teamWatcher: TeamWatcher;
   readonly tunnelManager: TunnelManager;
   readonly pushStore: PushSubscriptionStore;
-  startScheduledRun(prompt: string, workingDir: string, durationMinutes: number): Promise<ScheduledRun>;
+  startScheduledRun(prompt: string, workingDir: string, durationMinutes: number, owner?: string): Promise<ScheduledRun>;
   stopScheduledRun(id: string): Promise<void>;
 }

src/web/public/admin-ui.js

@@ -0,0 +1,557 @@
+/**
+ * @fileoverview Multi-user frontend: identity boot, admin Users panel, the
+ * change-password flow, and the full Admin Panel modal (user CRUD, per-user
+ * permissions, case-folder management) opened by the header Admin Panel button
+ * (#adminPanelBtn, revealed for admins in multi-user mode). Self-contained
+ * (builds its own DOM) so it needs no index.html surgery beyond the script tag
+ * and button; integrates with the existing App Settings modal by injecting a
+ * "Users" tab (admins in multi-user mode only). Live-refreshes on the SSE
+ * admin:usersChanged event (wired in app.js → window.codemanAdmin.onUsersChanged).
+ *
+ * @dependency app.js (window.app), settings-ui.js (App Settings modal + tab switch)
+ * @loadorder after settings-ui.js / ultracode-panel.js, before session-ui.js
+ *
+ * In single-user mode GET /api/me returns a synthetic admin with multiUser:false,
+ * so none of the admin UI is shown and behavior is unchanged.
+ */
+(function () {
+  'use strict';
+
+  const unwrap = (body) => (body && typeof body === 'object' && 'data' in body ? body.data : body);
+
+  async function apiGet(path) {
+    const res = await window.fetch(path, { headers: { Accept: 'application/json' } });
+    return unwrap(await res.json());
+  }
+  async function apiSend(method, path, body) {
+    const res = await window.fetch(path, {
+      method,
+      headers: body ? { 'Content-Type': 'application/json' } : {},
+      body: body ? JSON.stringify(body) : undefined,
+    });
+    let json = null;
+    try {
+      json = await res.json();
+    } catch {
+      /* empty body */
+    }
+    return { ok: res.ok, status: res.status, body: json, data: unwrap(json) };
+  }
+
+  // ── Change-password modal ─────────────────────────────────────────────────
+  let cpModal = null;
+  function buildChangePasswordModal() {
+    if (cpModal) return cpModal;
+    const el = document.createElement('div');
+    el.className = 'modal';
+    el.id = 'changePasswordModal';
+    el.style.zIndex = '3100';
+    el.innerHTML = `
+      <div class="modal-content" style="max-width:420px">
+        <div class="modal-header"><h2>Change Password</h2></div>
+        <div class="modal-body">
+          <p id="cpMustNote" class="form-hint" style="display:none;color:var(--warning,#c80)">
+            You must change your password before continuing.</p>
+          <div class="form-row"><label>Current password</label>
+            <input type="password" id="cpCurrent" class="form-input" autocomplete="current-password"></div>
+          <div class="form-row"><label>New password (min 8)</label>
+            <input type="password" id="cpNew" class="form-input" autocomplete="new-password"></div>
+          <div class="form-row"><label>Confirm new password</label>
+            <input type="password" id="cpConfirm" class="form-input" autocomplete="new-password"></div>
+          <p id="cpError" style="color:var(--error,#c33);min-height:1.2em"></p>
+        </div>
+        <div class="modal-footer">
+          <button class="btn" id="cpCancel">Cancel</button>
+          <button class="btn btn-primary" id="cpSubmit">Change password</button>
+        </div>
+      </div>`;
+    document.body.appendChild(el);
+    el.querySelector('#cpCancel').onclick = () => (el.style.display = 'none');
+    el.querySelector('#cpSubmit').onclick = async () => {
+      const current = el.querySelector('#cpCurrent').value;
+      const nw = el.querySelector('#cpNew').value;
+      const confirm = el.querySelector('#cpConfirm').value;
+      const err = el.querySelector('#cpError');
+      err.textContent = '';
+      if (nw.length < 8) return (err.textContent = 'New password must be at least 8 characters.');
+      if (nw !== confirm) return (err.textContent = 'Passwords do not match.');
+      const r = await apiSend('POST', '/api/me/password', { currentPassword: current, newPassword: nw });
+      if (!r.ok) return (err.textContent = (r.body && r.body.error) || 'Change failed.');
+      el.style.display = 'none';
+      if (window.app && window.app.showToast) window.app.showToast('Password changed');
+    };
+    cpModal = el;
+    return el;
+  }
+  function openChangePassword(forced) {
+    const el = buildChangePasswordModal();
+    el.querySelector('#cpMustNote').style.display = forced ? '' : 'none';
+    el.querySelector('#cpCancel').style.display = forced ? 'none' : '';
+    el.querySelector('#cpError').textContent = '';
+    el.style.display = 'flex';
+  }
+
+  // ── Fetch interceptor: surface PASSWORD_CHANGE_REQUIRED ───────────────────
+  function installInterceptor() {
+    const orig = window.fetch;
+    window.fetch = async function (...args) {
+      const res = await orig.apply(this, args);
+      if (res.status === 403) {
+        try {
+          const clone = res.clone();
+          const j = await clone.json();
+          if (j && j.errorCode === 'PASSWORD_CHANGE_REQUIRED') openChangePassword(true);
+        } catch {
+          /* not JSON */
+        }
+      }
+      return res;
+    };
+  }
+
+  // ── Admin Users panel (injected into the App Settings modal) ──────────────
+  function injectUsersTab() {
+    const modal = document.getElementById('appSettingsModal');
+    if (!modal || modal.querySelector('[data-tab="settings-users"]')) return;
+    const tabs = modal.querySelector('.modal-tabs');
+    const body = modal.querySelector('.modal-body');
+    if (!tabs || !body) return;
+    const btn = document.createElement('button');
+    btn.className = 'modal-tab-btn';
+    btn.dataset.tab = 'settings-users';
+    btn.textContent = 'Users';
+    tabs.appendChild(btn);
+    const content = document.createElement('div');
+    content.className = 'modal-tab-content hidden';
+    content.id = 'settings-users';
+    content.innerHTML = `
+      <div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:8px">
+        <strong>Users</strong>
+        <span>
+          <button class="btn btn-sm" id="adminOpenPanel">Open Admin Panel</button>
+          <button class="btn btn-sm" id="adminAddUser">+ Add user</button>
+        </span>
+      </div>
+      <p class="form-hint">Users share the host account; this separates workspaces, it does not sandbox
+        users from each other. Pair with Docker cases for isolation.</p>
+      <div id="adminUsersTable"></div>
+      <p id="adminUsersMsg" style="min-height:1.2em;color:var(--muted,#888)"></p>`;
+    body.appendChild(content);
+    // Render whenever the tab is shown (the shared switchSettingsTab toggles it).
+    btn.addEventListener('click', renderUsers);
+    content.querySelector('#adminAddUser').onclick = addUserFlow;
+    content.querySelector('#adminOpenPanel').onclick = openAdminPanel;
+  }
+
+  function esc(s) {
+    return String(s).replace(/[&<>"]/g, (c) => ({ '&': '&amp;', '<': '&lt;', '>': '&gt;', '"': '&quot;' })[c]);
+  }
+
+  async function renderUsers() {
+    const table = document.getElementById('adminUsersTable');
+    if (!table) return;
+    table.innerHTML = 'Loading…';
+    let users;
+    try {
+      users = await apiGet('/api/admin/users');
+    } catch {
+      table.innerHTML = 'Failed to load users.';
+      return;
+    }
+    const rows = users
+      .map((u) => {
+        const flags = [
+          u.role === 'admin' ? 'admin' : 'user',
+          u.disabled ? 'disabled' : 'enabled',
+          u.canBypassPermissions ? 'can-bypass' : '',
+          u.mustChangePassword ? 'must-change-pw' : '',
+        ]
+          .filter(Boolean)
+          .join(', ');
+        const st = u.stats || {};
+        return `<tr data-u="${esc(u.username)}">
+          <td>${esc(u.username)}</td>
+          <td style="font-size:.85em;color:var(--muted,#888)">${esc(flags)}</td>
+          <td style="font-size:.85em">${st.liveSessions ?? 0} live · ${st.caseCount ?? 0} cases</td>
+          <td style="white-space:nowrap">
+            <button class="btn btn-xs" data-act="role">${u.role === 'admin' ? 'Demote' : 'Promote'}</button>
+            <button class="btn btn-xs" data-act="disabled">${u.disabled ? 'Enable' : 'Disable'}</button>
+            <button class="btn btn-xs" data-act="bypass">${u.canBypassPermissions ? 'Revoke bypass' : 'Grant bypass'}</button>
+            <button class="btn btn-xs" data-act="reset">Reset pw</button>
+            <button class="btn btn-xs" data-act="delete">Delete</button>
+          </td></tr>`;
+      })
+      .join('');
+    table.innerHTML = `<table style="width:100%;border-collapse:collapse" class="admin-users">
+      <thead><tr><th align="left">User</th><th align="left">Flags</th><th align="left">Usage</th><th></th></tr></thead>
+      <tbody>${rows}</tbody></table>`;
+    table.querySelectorAll('button[data-act]').forEach((b) => {
+      b.onclick = () =>
+        userAction(
+          b.closest('tr').dataset.u,
+          b.dataset.act,
+          users.find((x) => x.username === b.closest('tr').dataset.u)
+        );
+    });
+  }
+
+  function setMsg(t) {
+    const m = document.getElementById('adminUsersMsg');
+    if (m) m.textContent = t || '';
+  }
+
+  async function userAction(username, act, u) {
+    if (act === 'role') {
+      const r = await apiSend('PATCH', `/api/admin/users/${encodeURIComponent(username)}`, {
+        role: u.role === 'admin' ? 'user' : 'admin',
+      });
+      setMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'disabled') {
+      const r = await apiSend('PATCH', `/api/admin/users/${encodeURIComponent(username)}`, { disabled: !u.disabled });
+      setMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'bypass') {
+      const r = await apiSend('PATCH', `/api/admin/users/${encodeURIComponent(username)}`, {
+        canBypassPermissions: !u.canBypassPermissions,
+      });
+      setMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'reset') {
+      if (!window.confirm(`Reset ${username}'s password? They must set a new one on next login.`)) return;
+      const r = await apiSend('POST', `/api/admin/users/${encodeURIComponent(username)}/reset-password`);
+      if (r.ok && r.data && r.data.oneTimePassword) {
+        window.prompt(`One-time password for ${username} (copy it now — shown once):`, r.data.oneTimePassword);
+      } else setMsg((r.body && r.body.error) || 'Reset failed.');
+    } else if (act === 'delete') {
+      const typed = window.prompt(`Type "${username}" to delete this user. Add " +space" to also delete their files.`);
+      if (typed !== username && typed !== `${username} +space`) return setMsg('Delete cancelled.');
+      const deleteSpace = typed.endsWith(' +space');
+      const r = await apiSend('DELETE', `/api/admin/users/${encodeURIComponent(username)}`, { deleteSpace });
+      setMsg(r.ok ? `Deleted ${username}.` : (r.body && r.body.error) || 'Delete failed.');
+    }
+    renderUsers();
+  }
+
+  async function addUserFlow() {
+    const username = window.prompt('New username (lowercase, 2-32 chars, [a-z0-9_-]):');
+    if (!username) return;
+    const admin = window.confirm('Make this user an admin? (OK = admin, Cancel = regular user)');
+    const r = await apiSend('POST', '/api/admin/users', { username: username.trim(), role: admin ? 'admin' : 'user' });
+    if (r.ok && r.data && r.data.oneTimePassword) {
+      window.prompt(`Created ${username}. One-time password (copy it now — shown once):`, r.data.oneTimePassword);
+    } else setMsg((r.body && r.body.error) || 'Create failed.');
+    renderUsers();
+  }
+
+  // ── Admin Panel (big header-button modal) ─────────────────────────────────
+  let apModal = null;
+  let apUsersCache = [];
+  const apOpenDrawers = new Set(); // usernames with an expanded case-folder drawer
+
+  function fmtDate(ts) {
+    return ts ? new Date(ts).toLocaleString() : 'never';
+  }
+  function cssEsc(s) {
+    return window.CSS && window.CSS.escape ? window.CSS.escape(s) : String(s).replace(/"/g, '\\"');
+  }
+  function apSetMsg(t) {
+    const m = document.getElementById('apMsg');
+    if (m) m.textContent = t || '';
+  }
+
+  function buildAdminPanel() {
+    if (apModal) return apModal;
+    const el = document.createElement('div');
+    el.className = 'modal';
+    el.id = 'adminPanelModal';
+    el.style.zIndex = '3000';
+    el.innerHTML = `
+      <div class="modal-content" style="max-width:940px;width:min(96vw,940px)">
+        <div class="modal-header" style="display:flex;justify-content:space-between;align-items:center;gap:12px">
+          <h2 style="display:flex;align-items:center;gap:8px;margin:0">
+            <svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"
+              stroke-linecap="round" stroke-linejoin="round" aria-hidden="true">
+              <path d="M12 22s8-4 8-10V5l-8-3-8 3v7c0 6 8 10 8 10z"/></svg>
+            Admin Panel</h2>
+          <span id="apIdentity" style="color:var(--text-muted,#888);font-size:.85em"></span>
+        </div>
+        <div class="modal-body" style="max-height:70vh;overflow-y:auto">
+          <div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:8px">
+            <strong>Users</strong>
+            <button class="btn btn-sm btn-primary" id="apAddToggle">+ Add user</button>
+          </div>
+          <div id="apAddForm" style="display:none;border:1px solid var(--border,#333);border-radius:8px;padding:10px;margin-bottom:10px">
+            <div style="display:flex;gap:10px;flex-wrap:wrap;align-items:flex-end">
+              <div class="form-row" style="margin:0"><label>Username</label>
+                <input id="apNewName" class="form-input" placeholder="lowercase a-z 0-9 _ -" style="width:170px"></div>
+              <div class="form-row" style="margin:0"><label>Role</label>
+                <select id="apNewRole" class="form-input" style="width:110px">
+                  <option value="user">user</option>
+                  <option value="admin">admin</option>
+                </select></div>
+              <div class="form-row" style="margin:0"><label>Password (optional)</label>
+                <input id="apNewPw" type="password" class="form-input" placeholder="blank = one-time pw"
+                  style="width:170px" autocomplete="new-password"></div>
+              <label style="display:flex;align-items:center;gap:5px;white-space:nowrap;margin-bottom:6px">
+                <input type="checkbox" id="apNewBypass"> allow bypass permissions</label>
+              <button class="btn btn-sm btn-primary" id="apCreateUser" style="margin-bottom:2px">Create</button>
+            </div>
+            <p class="form-hint" style="margin:6px 0 0">Without a password a one-time password is generated and shown
+              once; the user must change it on first login. "Bypass" allows shell sessions, cron launch commands, and
+              skip-permissions agents.</p>
+          </div>
+          <div id="apOtp" style="display:none;border:1px solid var(--accent,#38b6f0);border-radius:8px;padding:10px;margin-bottom:10px"></div>
+          <div id="apTable">Loading…</div>
+          <p class="form-hint" style="margin-top:10px">Users share the host OS account: this separates workspaces, it
+            does not sandbox users from each other. Pair with Docker cases for isolation.</p>
+          <p id="apMsg" style="min-height:1.2em;color:var(--text-muted,#888)"></p>
+        </div>
+        <div class="modal-footer">
+          <button class="btn" id="apClose">Close</button>
+        </div>
+      </div>`;
+    document.body.appendChild(el);
+    el.querySelector('#apClose').onclick = () => (el.style.display = 'none');
+    el.addEventListener('click', (e) => {
+      if (e.target === el) el.style.display = 'none';
+    });
+    el.querySelector('#apAddToggle').onclick = () => {
+      const f = el.querySelector('#apAddForm');
+      f.style.display = f.style.display === 'none' ? '' : 'none';
+      if (f.style.display === '') f.querySelector('#apNewName').focus();
+    };
+    el.querySelector('#apCreateUser').onclick = createUserFromForm;
+    apModal = el;
+    return el;
+  }
+
+  function showOneTimePassword(username, otp) {
+    const box = document.getElementById('apOtp');
+    if (!box) return;
+    box.style.display = '';
+    box.innerHTML = `One-time password for <strong>${esc(username)}</strong> (shown once, copy it now):
+      <code style="user-select:all;font-size:1.05em;margin:0 8px">${esc(otp)}</code>
+      <button class="btn btn-xs" id="apOtpCopy">Copy</button>
+      <button class="btn btn-xs" id="apOtpDismiss">Dismiss</button>`;
+    box.querySelector('#apOtpCopy').onclick = () => {
+      if (navigator.clipboard) {
+        navigator.clipboard.writeText(otp).then(() => apSetMsg('Password copied to clipboard.'));
+      }
+    };
+    box.querySelector('#apOtpDismiss').onclick = () => {
+      box.style.display = 'none';
+      box.innerHTML = '';
+    };
+  }
+
+  async function createUserFromForm() {
+    const name = (document.getElementById('apNewName').value || '').trim().toLowerCase();
+    const role = document.getElementById('apNewRole').value;
+    const pw = document.getElementById('apNewPw').value;
+    const bypass = document.getElementById('apNewBypass').checked;
+    if (!name) return apSetMsg('Enter a username.');
+    const body = { username: name, role };
+    if (pw) body.password = pw;
+    if (bypass) body.canBypassPermissions = true;
+    const r = await apiSend('POST', '/api/admin/users', body);
+    if (!r.ok) return apSetMsg((r.body && r.body.error) || 'Create failed.');
+    document.getElementById('apNewName').value = '';
+    document.getElementById('apNewPw').value = '';
+    document.getElementById('apNewBypass').checked = false;
+    apSetMsg(`Created ${name}.`);
+    if (r.data && r.data.oneTimePassword) showOneTimePassword(name, r.data.oneTimePassword);
+    renderPanel();
+  }
+
+  async function renderPanel() {
+    const table = document.getElementById('apTable');
+    if (!table) return;
+    let users;
+    try {
+      users = await apiGet('/api/admin/users');
+    } catch {
+      table.innerHTML = 'Failed to load users.';
+      return;
+    }
+    apUsersCache = users;
+    const meName = (window.__codemanUser || {}).username;
+    const rows = users
+      .map((u) => {
+        const st = u.stats || {};
+        const you = u.username === meName ? ' <span style="color:var(--accent,#38b6f0)">(you)</span>' : '';
+        const role = `<span style="font-weight:600;color:${
+          u.role === 'admin' ? 'var(--accent,#38b6f0)' : 'var(--text-muted,#888)'
+        }">${u.role}</span>`;
+        const status = u.disabled
+          ? '<span style="color:var(--red,#c33)">disabled</span>'
+          : '<span style="color:var(--accent-soft,#4b9)">enabled</span>';
+        const pwFlag = u.mustChangePassword ? ' · must-change-pw' : '';
+        return `<tr data-u="${esc(u.username)}">
+          <td><strong>${esc(u.username)}</strong>${you}</td>
+          <td>${role}</td>
+          <td>${status}${pwFlag}</td>
+          <td>${u.canBypassPermissions ? 'yes' : 'no'}</td>
+          <td style="white-space:nowrap">${st.liveSessions ?? 0} live · ${st.activeSessions ?? 0} logins ·
+            <button class="btn btn-xs" data-act="cases">${st.caseCount ?? 0} cases</button></td>
+          <td style="font-size:.85em;color:var(--text-muted,#888)">${fmtDate(u.lastLoginAt)}</td>
+          <td style="white-space:nowrap">
+            <button class="btn btn-xs" data-act="role">${u.role === 'admin' ? 'Demote' : 'Promote'}</button>
+            <button class="btn btn-xs" data-act="disabled">${u.disabled ? 'Enable' : 'Disable'}</button>
+            <button class="btn btn-xs" data-act="bypass">${u.canBypassPermissions ? 'Revoke bypass' : 'Grant bypass'}</button>
+            <button class="btn btn-xs" data-act="reset">Reset pw</button>
+            <button class="btn btn-xs" data-act="logout">Logout</button>
+            <button class="btn btn-xs" data-act="delete" style="color:var(--red,#c33)">Delete</button>
+          </td></tr>
+          <tr data-drawer="${esc(u.username)}" style="display:none"><td colspan="7"></td></tr>`;
+      })
+      .join('');
+    table.innerHTML = `<table style="width:100%;border-collapse:collapse" class="admin-users">
+      <thead><tr>
+        <th align="left">User</th><th align="left">Role</th><th align="left">Status</th>
+        <th align="left">Bypass</th><th align="left">Activity</th><th align="left">Last login</th><th></th>
+      </tr></thead><tbody>${rows}</tbody></table>`;
+    table.querySelectorAll('button[data-act]').forEach((b) => {
+      const username = b.closest('tr').dataset.u;
+      b.onclick = () => {
+        if (b.dataset.act === 'cases') return toggleCaseDrawer(username);
+        return panelAction(
+          username,
+          b.dataset.act,
+          apUsersCache.find((x) => x.username === username)
+        );
+      };
+    });
+    // Re-open drawers that were expanded before this refresh.
+    for (const name of [...apOpenDrawers]) {
+      if (users.some((u) => u.username === name)) void renderCaseDrawer(name);
+      else apOpenDrawers.delete(name);
+    }
+  }
+
+  async function panelAction(username, act, u) {
+    const path = `/api/admin/users/${encodeURIComponent(username)}`;
+    if (act === 'role') {
+      const r = await apiSend('PATCH', path, { role: u.role === 'admin' ? 'user' : 'admin' });
+      apSetMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'disabled') {
+      const r = await apiSend('PATCH', path, { disabled: !u.disabled });
+      apSetMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'bypass') {
+      const r = await apiSend('PATCH', path, { canBypassPermissions: !u.canBypassPermissions });
+      apSetMsg(r.ok ? `Updated ${username}.` : (r.body && r.body.error) || 'Failed.');
+    } else if (act === 'reset') {
+      if (!window.confirm(`Reset ${username}'s password? They must set a new one on next login.`)) return;
+      const r = await apiSend('POST', `${path}/reset-password`);
+      if (r.ok && r.data && r.data.oneTimePassword) showOneTimePassword(username, r.data.oneTimePassword);
+      else if (!r.ok) apSetMsg((r.body && r.body.error) || 'Reset failed.');
+    } else if (act === 'logout') {
+      const r = await apiSend('POST', `${path}/logout`);
+      apSetMsg(r.ok ? `Revoked ${(r.data && r.data.revoked) || 0} login session(s) for ${username}.` : 'Failed.');
+    } else if (act === 'delete') {
+      if (!window.confirm(`Delete user "${username}"? Their live sessions are killed and logins revoked.`)) return;
+      const deleteSpace = window.confirm(
+        `Also delete ${username}'s files (their cases/workspace folder)?\nOK = delete files too, Cancel = keep files on disk.`
+      );
+      const r = await apiSend('DELETE', path, { deleteSpace });
+      apSetMsg(r.ok ? `Deleted ${username}.` : (r.body && r.body.error) || 'Delete failed.');
+    }
+    renderPanel();
+  }
+
+  async function toggleCaseDrawer(username) {
+    if (apOpenDrawers.has(username)) {
+      apOpenDrawers.delete(username);
+      const row = apModal && apModal.querySelector(`tr[data-drawer="${cssEsc(username)}"]`);
+      if (row) row.style.display = 'none';
+      return;
+    }
+    apOpenDrawers.add(username);
+    await renderCaseDrawer(username);
+  }
+
+  async function renderCaseDrawer(username) {
+    const row = apModal && apModal.querySelector(`tr[data-drawer="${cssEsc(username)}"]`);
+    if (!row) return;
+    row.style.display = '';
+    const cell = row.firstElementChild;
+    cell.innerHTML = 'Loading folders…';
+    let data;
+    try {
+      data = await apiGet(`/api/admin/users/${encodeURIComponent(username)}/cases`);
+    } catch {
+      cell.innerHTML = 'Failed to load case folders.';
+      return;
+    }
+    const items = (data.cases || [])
+      .map(
+        (c) => `
+      <li style="display:flex;gap:10px;align-items:center;padding:2px 0">
+        <code>${esc(c.name)}</code>
+        <span style="color:var(--text-muted,#888);font-size:.85em">${fmtDate(c.modifiedAt)}</span>
+        ${c.liveSessions ? `<span style="color:var(--yellow,#ca0)">${c.liveSessions} live session(s)</span>` : ''}
+        <button class="btn btn-xs" data-case="${esc(c.name)}"
+          ${c.liveSessions ? 'disabled title="In use by a live session"' : ''}>Delete</button>
+      </li>`
+      )
+      .join('');
+    cell.innerHTML = `<div style="padding:6px 4px 6px 16px">
+      <div style="color:var(--text-muted,#888);font-size:.85em;margin-bottom:4px">${esc(data.dir || '')}</div>
+      ${items ? `<ul style="list-style:none;margin:0;padding:0">${items}</ul>` : 'No case folders yet.'}
+    </div>`;
+    cell.querySelectorAll('button[data-case]').forEach((b) => {
+      b.onclick = async () => {
+        const name = b.dataset.case;
+        if (!window.confirm(`Permanently delete ${username}'s case folder "${name}" and ALL files in it?`)) return;
+        const r = await apiSend(
+          'DELETE',
+          `/api/admin/users/${encodeURIComponent(username)}/cases/${encodeURIComponent(name)}`
+        );
+        apSetMsg(r.ok ? `Deleted folder ${name}.` : (r.body && r.body.error) || 'Delete failed.');
+        renderPanel();
+      };
+    });
+  }
+
+  function openAdminPanel() {
+    const me = window.__codemanUser || {};
+    if (!me.multiUser || me.role !== 'admin') return;
+    const el = buildAdminPanel();
+    el.querySelector('#apIdentity').textContent = `signed in as ${me.username} (admin)`;
+    apSetMsg('');
+    el.style.display = 'flex';
+    renderPanel();
+  }
+
+  /** SSE admin:usersChanged: live-refresh whichever admin views are visible. */
+  function onUsersChanged() {
+    if (apModal && apModal.style.display === 'flex') renderPanel();
+    const tab = document.getElementById('settings-users');
+    if (tab && !tab.classList.contains('hidden')) renderUsers();
+  }
+
+  // ── Boot ──────────────────────────────────────────────────────────────────
+  async function boot() {
+    installInterceptor();
+    let me = null;
+    try {
+      me = await apiGet('/api/me');
+    } catch {
+      /* server may be pre-auth */
+    }
+    window.__codemanUser = me || { username: 'admin', role: 'admin', multiUser: false };
+    document.dispatchEvent(new CustomEvent('codeman:me', { detail: window.__codemanUser }));
+    if (window.__codemanUser.mustChangePassword) openChangePassword(true);
+    if (window.__codemanUser.multiUser && window.__codemanUser.role === 'admin') {
+      injectUsersTab();
+      // Reveal the big header Admin Panel button (template ships it hidden).
+      const btn = document.getElementById('adminPanelBtn');
+      if (btn) btn.classList.remove('btn-admin-panel--hidden');
+    }
+  }
+
+  if (document.readyState === 'loading') {
+    document.addEventListener('DOMContentLoaded', boot);
+  } else {
+    boot();
+  }
+
+  window.codemanAdmin = { openChangePassword, renderUsers, openAdminPanel, onUsersChanged };
+})();