feat(server-s3): one Linux user per account (S3) — experimental

Server mode can now run each account as its own Linux user (ah-<name>)
when `agenthub server install-system` has set S3 up. The dashboard
reaches a member only through sudo -u / write-as / pane-launch, reads a
member's files only through owner- and type-checked opens, and hooks
are authenticated by peer uid. Local mode and server mode without S3
are unchanged.

EXPERIMENTAL: tested with fake sudo and fake accounts only. It has not
yet been verified on a real install with real member accounts, sudo or
a real Codex login. Do not offer it to real users yet.

- S3 core: provisioning, per-member tmux servers, the proxy key
  gateway, shared tools in /opt, dropped capabilities for children
  (P0–P5)
- P4: plan and quota per member home
- P6: ~/.claude.json seed; opt-in plugin baseline installed as the
  member; managed-settings spike script (not run)
- P7: Codex account pool (`agenthub accounts add --tool codex`)
- Roles merged with main's admin / analyst / developer: analysts write
  only their own rows, under S3 as well
- Per-account prefs: one implementation (Chat UI + onboarding)
- Security reviews F1–F49 (five rounds), each fix with a regression
  test: symlink/TOCTOU-safe member reads, no host writes in a member
  home, credentials and the data dir never served, owner and folder
  account must agree, pane tokens bound to the pane's uid, bounded
  sudo/tmux/git calls and member reads (no hang or crash from a member),
  async route rejections answer 500 instead of exiting
- Docs: docs/SERVER-MODE.md (S3 model, accepted ceilings, operator
  runbook), docs/plans/server-mode/S3-PLAN.md, CLAUDE.md S3 rules

Tests: server 2838/2841 (3 need 127.0.0.1:3000, held on this box);
client 1162/1162; tsc clean; headers check passes.

Co-Authored-By: Claude <noreply@anthropic.com>

CLAUDE.md

@@ -1,6 +1,6 @@
 # Claude Code Working Guide
 
-_Last synced: v2.5.13 (2026-10-08) — roles admin/analyst/developer (`usePermissions`), Chat UI per account (Settings → Appearance, `/api/me/prefs`, `PaneChat.tsx`), one shared terminal size per pane (`pty-attach.js`). Older sync history: `docs/CLAUDE-SYNC-LOG.md` (archive, not loaded)._ A change that makes any statement in this file, `AGENTS.md`, or a README wrong — a moved path, a new or changed extension point, a retired rule — updates that file in the same change-set and bumps this marker. **Bump = replace the version/date and a ≤ 1-line summary; never append a changelog here** — details belong in the commit message and `docs/`, because this whole file is loaded into every session.
+_Last synced: v2.5.13 + S3 P4–P8 (2026-10-09) — S3 review round 5: host folders admin-only, pane cwd/token bound to the pane's account, bounded sudo, capped member reads (`readLines`). Older sync history: `docs/CLAUDE-SYNC-LOG.md` (archive, not loaded)._ A change that makes any statement in this file, `AGENTS.md`, or a README wrong — a moved path, a new or changed extension point, a retired rule — updates that file in the same change-set and bumps this marker. **Bump = replace the version/date and a ≤ 1-line summary; never append a changelog here** — details belong in the commit message and `docs/`, because this whole file is loaded into every session.
 
 ## Project mission
 - Maintain a reliable local-first dashboard for Claude Code session monitoring.
@@ -76,8 +76,9 @@ See `docs/LANES.md` for full guide: stage reporting, custom templates, lane acti
 - **A session reload is typed into a live pane, never spawned.** `/reload-plugins` and `/reload-skills` are scoped BY CLAUDE CODE to the session that runs them, so nothing can reload a session from the outside. `server/lib/cc-reload.js` therefore types them into the dashboard's existing tmux lane panes and spawns NO `claude` process — a one-shot `claude -p "/reload-plugins"` reloads only its own short-lived session, exits, and leaves a junk session in the dashboard's own history. Do not add a path that starts a session in order to reload one.
 - **A read that scans the events table never runs on the event loop, and never runs a correlated subquery per event.** Node serves every page, hook and websocket from one thread, and better-sqlite3/node:sqlite block it for the whole query — one slow aggregate freezes the dashboard for every user. Put an aggregate that takes more than a few hundred ms at real size into `JOBS` in `server/lib/read-pool.js` (its own `query_only` connection in a worker, timeout, shared in-flight runs); write "the next event of the session" as a window function (`LEAD() OVER (PARTITION BY session_id ORDER BY id)`), not `MIN(id) … id > e1.id`. And do not drop `idx_events_session(session_id, id)` as a "prefix" of another index: only it orders a session's events by id.
 - **A headless entry point requires `server/lib/windows-hide.js` before anything reads `child_process`.** The dashboard and its detached helpers have no console on Windows, so every git/npm call without `windowsHide` opened a console window that flashed and stole focus on each poll. `install()` (in `server/index.js`, `plugin-bootstrap.js`, `plugin-update-helper.js`, `cc-update-all-helper.js`, `restart-helper.js`) forces it for every spawn; a new detached script needs the same first line, or a `windowsHide: true` of its own (the statusline's one git call has that).
-- **Server mode is a MODE of this codebase, never a fork, and local mode must not notice it.** Everything server-only checks `isServerMode()` (`AGENTHUB_MODE=server`, `server/lib/auth.js`) and is a no-op otherwise; `auth.js` opens the database only on first use, so a module that merely loads it never touches the DB in local mode. Accounts are made from the host's shell (`agenthub server setup`, `agenthub users …`) or by an admin on the Users page (`server/routes/users.js`), where EVERY change needs the admin's own password again (`confirmPassword` in `auth.js`, throttled — EREAUTH/ETOOMANY), never lets an admin demote or disable themselves (ESELF), is written to `audit_log`, and refuses in local mode (ELOCALMODE: no login to check) — do not add an account route without that step-up, and never one that returns a password hash. Rows are OWNED (phase S2, `server/lib/scope.js`): `lanes.owner_id` is the creator (never from the request — `ownerFor(req)`), a session belongs to its workspace (`sessions.lane_id` or a `dashboard_runs` row), and everything else hangs off the session. A `developer` sees only their own rows, and an `analyst` reads every row but writes only their own (`memberId` scopes an analyst's non-GET requests like a developer's — `member` was renamed `developer`, `db.js` migrates it): every list/aggregate passes `req` into `sessionWhere`/`bySessionWhere`/`laneWhere`; every route naming ONE row is covered by `scopeGuard`'s `PATH_RULES` + the query/body id names in `namedIds` (404 `ENOTFOUND`) — a new id route under a new prefix needs a rule there; every WebSocket broadcast type needs a `broadcastAudience` case (an unlisted type reaches no developer); a staff-wide view joins `STAFF_ONLY_PREFIXES`. Admin/analyst reads of a developer's session are written to `audit_log` (`server/lib/audit.js`). A pane carries `AGENTHUB_PANE_TOKEN` (hash in `dashboard_runs.pane_token_hash`, never listed) so the CLI/MCP/statusline inside it act as the workspace owner — accepted only from loopback and only while the pane lives (`userFromPaneToken`). Every write in server mode passes the Origin check in `authGuard`; prefix checks go through `apiPath()` (decoded, case-insensitive), because Express routes `/api/Webhooks` and `%77ebhooks` too. Named locks are namespaced per user, and `named-lock.js` takes only a plain name (a lock name was a path). It is still NOT OS isolation: every pane runs as the host account until S3, so do not call it multi-tenant. A new route that writes the host's own configuration joins `ADMIN_WRITE_PREFIXES`, and its controls hide behind `usePermissions().isAdmin` (`client/src/components/AuthGate.tsx`) — a hidden button is a courtesy, the server's refusal is the rule; hooks stay loopback-only in server mode.
-- **A pool token reaches a pane only through tmux `-e`, and only for the account `pickAccount` chose.** Never type it into a pane, never put it in the CLI's argv, never return it from a route (`poolStatus` has no token field), and never add a route that adds or reads one — the pool is filled from the host's shell (`agenthub accounts add`). An empty pool must leave every spawn exactly as before.
+- **Server mode is a MODE of this codebase, never a fork, and local mode must not notice it.** Everything server-only checks `isServerMode()` (`AGENTHUB_MODE=server`, `server/lib/auth.js`) and is a no-op otherwise; `auth.js` opens the database only on first use, so a module that merely loads it never touches the DB in local mode. Accounts are made from the host's shell (`agenthub server setup`, `agenthub users …`) or by an admin on the Users page (`server/routes/users.js`), where EVERY change needs the admin's own password again (`confirmPassword` in `auth.js`, throttled — EREAUTH/ETOOMANY), never lets an admin demote or disable themselves (ESELF), is written to `audit_log`, and refuses in local mode (ELOCALMODE: no login to check) — do not add an account route without that step-up, and never one that returns a password hash. Rows are OWNED (phase S2, `server/lib/scope.js`): `lanes.owner_id` is the creator (never from the request — `ownerFor(req)`), a session belongs to its workspace (`sessions.lane_id` or a `dashboard_runs` row), and everything else hangs off the session. A `developer` sees only their own rows, and an `analyst` reads every row but writes only their own (`memberId` scopes an analyst's non-GET requests like a developer's — `member` was renamed `developer`, `db.js` migrates it): every list/aggregate passes `req` into `sessionWhere`/`bySessionWhere`/`laneWhere`; every route naming ONE row is covered by `scopeGuard`'s `PATH_RULES` + the query/body id names in `namedIds` (404 `ENOTFOUND`) — a new id route under a new prefix needs a rule there; every WebSocket broadcast type needs a `broadcastAudience` case (an unlisted type reaches no developer); a staff-wide view joins `STAFF_ONLY_PREFIXES`. Admin/analyst reads of a developer's session are written to `audit_log` (`server/lib/audit.js`). A pane carries `AGENTHUB_PANE_TOKEN` (hash in `dashboard_runs.pane_token_hash`, never listed) so the CLI/MCP/statusline inside it act as the workspace owner — accepted only from loopback and only while the pane lives (`userFromPaneToken`). Every write in server mode passes the Origin check in `authGuard`; prefix checks go through `apiPath()` (decoded, case-insensitive), because Express routes `/api/Webhooks` and `%77ebhooks` too. Named locks are namespaced per user, and `named-lock.js` takes only a plain name (a lock name was a path). It is NOT OS isolation unless S3 is installed (next rule); without it every pane runs as the host account, so do not call that multi-tenant. A new route that writes the host's own configuration joins `ADMIN_WRITE_PREFIXES`, and its controls hide behind `usePermissions().isAdmin` (`client/src/components/AuthGate.tsx`) — a hidden button is a courtesy, the server's refusal is the rule; hooks stay loopback-only in server mode.
+- **With S3 installed (server mode + `/etc/agenthub/server.conf`, `s3Enabled`), a pane runs as its workspace owner's Linux user, and the dashboard reaches a member only through sudo.** `ah-<name>`, home `<USERS_ROOT>/<name>`; the FOLDER decides (`accountForPath` in `server/lib/run-as.js`), and a folder under the users root with no enabled, provisioned user is `EMEMBERGONE` — never fall back to the host there. Every tmux call on a member's socket (attach included), every git/`gh` call in a member's folder and every write is `sudo -n -u ah-<name> <tmux|git|gh|write-as>` by the absolute paths in `server.conf` (`sudoArgv`); sudoers allows exactly those, plus `/opt/agenthub/tools/bin/claude` for the opt-in plugin baseline (`applyPluginBaseline`), as `%agenthub-members` and NEVER root as a run-as target. **The only root commands are `/opt/agenthub/sbin/agenthub-provision` (create/disable/enable — it never deletes, never adopts a non-member account, and root never touches a path inside an existing home) and `systemctl start|stop|restart|enable|disable agenthub.service`;** do not add a third — a host compromise is already every member's. **sudo logs argv, so nothing secret or private crosses it:** a member pane's env (pane token, pool token) and command (prompt) go in a launch file written by `write-as` from stdin and run by `pane-launch`; file content always goes on stdin. **The host never writes, chmods or deletes inside a member's home itself — only through `write-as` as the member** (`writeFileAs`, `handoffWrite`, `mkdirAs`, `removeAs`, `scratchFile`): the member can swap any name there for a link, and the host's write would follow it. A member's file is READ only through `openSafe`/`readFileSafe*`/`readStreamSafe` (open, then `fstat`: a regular file that member owns, `O_NONBLOCK`), never a plain `fs` read. **Hooks are authenticated by the peer uid** of the loopback connection (`/proc/net/tcp*`, `server/lib/hook-auth.js`), never by anything in the body: host or root = trusted, an enabled `ah-*` = only work, sessions, runs and transcript paths inside its own home (`EFOREIGN`, foreign paths dropped BEFORE any tool mapping reads them), anyone else `EPEER`. **`hidepid=invisible` (gid `agenthub-proc` exempt) is required** — panes' argv/env would otherwise be readable by every account — and `install-system` stops without it. The unit's ambient `CAP_DAC_READ_SEARCH` is dropped for every child (`server/lib/drop-caps.js`, installed first in `server/index.js`, before anything reads `child_process`) — keep it there, and a spawn outside `child_process` (node-pty) takes `ptyArgv`. **The account comes from a path's TEXT, so a path a member can redirect is checked before it is used:** a workspace's real path (`laneRoot` in `git-diff.js`, `EFOREIGN`) and a git dir their git prints (`git-exclude.js`) must stay the same account's (`sameOwner`), a member's home is no workspace, and a READ uses `ownerForRead`, never the throwing `accountForPath`. **A workspace inside a member's home is owned by that member only, and one outside the users root (it runs as the HOST) by an admin only, by the LIVE role** (`assertOwnerFits`: create, assign, every pane start — `EOWNERFOLDER`; demoting or disabling a user ends their host panes): its panes run as the FOLDER's account but carry the OWNER's pane token, which that account can read; a pane's cwd must be that same account's (`ECWDACCOUNT`), and a pane token is accepted only from that account's uid (`peerIsPaneAccount`). A path a non-admin names in ANY request (an analyst's GET too) stays in their own folder or workspaces (`ownFolder`, `insideOwnWorkspace`, `scope.ownCwdQuery`), and the config `file` reads never serve a credential file or anything in the data dir (`isSecretConfigPath`). **A member can stall or flood what the dashboard reads, and it all runs on one thread:** every synchronous sudo into a member is time-bounded (`MEMBER_EXEC`, tmux `memberCall` with a back-off) and a member's tmux failure makes only THEIR panes unknown, never everyone's; a member's file is read with a size cap (`readFileSafe*` `max`), line by line only through `readLines` (never `readline`, which a one-line 512 MB file crashes), and a sparse one is never copied out as real blocks. Operator steps: `docs/SERVER-MODE.md` § Operator runbook.
+- **A pool token reaches a pane only through tmux `-e` (a member's pane under S3: its launch file), and only for the account `pickAccount` chose.** Never type it into a pane, never put it in the CLI's argv, never return it from a route (`poolStatus` has no token field), and never add a route that adds or reads one — the pool is filled from the host's shell (`agenthub accounts add [--tool codex]`). An empty pool must leave every spawn exactly as before. The ONE exception is a Codex ChatGPT login (`server/lib/codex-pool.js`), which Codex reads from no env var: it is written as `auth.json` into a MEMBER's own CODEX_HOME, as the member (`write-as`, 0600), never into a host pane's CODEX_HOME, never over a login AgentHub did not place, and never a second account into a home where a live pane of that member runs on one; `syncBack` copies the newest back. A Codex API key is `-e AGENTHUB_POOL_KEY` plus a `-c` provider whose `env_key` only names it.
 - Preserve existing behavior unless explicitly asked to change it.
 - Prefer minimal, reversible diffs.
 - Never silently weaken safety controls around destructive actions.