feat(agent): confine agent file/shell tools to a selectable workspace (#3665)

* feat(agent): workspace confinement via context-local binding + get_workspace tool

Bind the per-turn workspace once in execute_tool_block; the shared path
resolvers (_resolve_tool_path / _resolve_search_root) and the subprocess cwd
helper (agent_cwd) read it, so file tools + bash/python are confined centrally
and a new tool that uses the shared helpers cannot accidentally bypass it.

Adds the admin-gated /api/workspace/browse picker, a workspace pill + directory
modal (reusing existing modal/button CSS), the /workspace slash command, and a
get_workspace tool (replaces a system-prompt block). Confinement is OS-agnostic
(realpath/normcase/commonpath) and docker-safe (container paths, no host
assumptions). Reopens #2023.

* ux(workspace): clarify workspace is not a sandbox

Picker modal note + pill tooltip + get_workspace tool/output wording now state
plainly: read_file/write_file/edit_file/grep/glob/ls are confined to the folder,
but bash/python only start there (cwd) and are not sandboxed. Modal note reuses
the existing .muted class.

* fix(agent): treat an active workspace as file-work intent

A vague low-signal message (e.g. "look at the local project") matches no
domain keywords, so tool retrieval is skipped and only always-available tools
are offered — leaving the agent with no file access even though a workspace is
set. When a workspace is active, include the file/code tools (incl.
get_workspace) on low-signal turns so the agent can act on the folder.

Also requires the tool index (ChromaDB) to be reachable for normal retrieval;
that is an environment dependency, not part of this change.

* ux(workspace): hide pill + overflow entry in chat mode

Workspace only scopes the agent's file/shell tools, so the pill and the
overflow 'Workspace' entry are agent-only now — hidden in chat mode like the
bash toggle. Mode read from the DOM in syncWorkspaceIndicator; applyMode() is
called from the agent/chat setMode handler.

* prompt(tools): steer bash/python to defer to the dedicated file tools

bash/python schema descriptions (what native-tool-calling models read) were
bare and gave no steer, so models would do file ops via the shell (e.g. writing
SVG/HTML, which then dumps raw markup into the tool preview). Tell bash/python
in the schema + tool-index + prompt section to prefer read_file/write_file/
edit_file/grep/glob/ls and only be used for what those do not cover.

* prompt(tools): keep bash/python deferral generic (no hardcoded tool names)

Reference 'a dedicated tool' rather than listing read_file/write_file/grep/etc.
by name, so the guidance does not go stale if those tools are renamed.

* style(workspace): drop em-dashes from added code comments/strings

* ux(workspace): terser non-sandbox note in picker (no tool-name list)

* ux(workspace): mirror terse non-sandbox wording in pill tooltip

* chore: untrack local venv symlink (run-only, not part of the feature)

* prompt(workspace): keep get_workspace text generic (no hardcoded tool names)

* fix(agent): low-signal + workspace surfaces only read-only file tools

Intersect the files tool group with PLAN_MODE_READONLY_TOOLS so a vague message
in a workspace exposes read_file/grep/glob/ls/get_workspace for exploration, but
not write_file/edit_file/bash/python -- those wait for a request that actually
calls for them (RAG retrieval still adds them on a real ask).

* feat(workspace): cap browse listing at 500 dirs with a truncated hint

Mirror the filesystem_tools._CODENAV_MAX_HITS pattern with a module-local
_MAX_BROWSE_DIRS so a directory with thousands of children does not dump every
row into the picker; the response carries a truncated flag and the modal tells
the user to type a path to jump in.

* chore: untrack local venv symlink (run-only artifact)

* fix(workspace): vet the workspace root against the sensitive-path deny list at bind time

The in-workspace resolver deny-lists sensitive paths inside the workspace,
but the empty-path search root is the workspace itself, so a workspace of
~/.ssh could be listed via ls with no path. vet_workspace() (public, in
tool_execution next to the resolvers) rejects non-directories and sensitive
roots before the path is ever bound; chat_routes uses it instead of its
inline isdir check.

* fix(workspace): reject filesystem roots and stop showing rejected workspaces as active

Review findings from #3665:

P2: vet_workspace accepted / (and would accept drive/UNC roots), which makes
every absolute path 'inside' the workspace and collapses confinement into
host-wide file access. A root is its own dirname, so reject when
dirname(resolved) == resolved; the browse response now carries a selectable
flag and the picker disables 'Use this folder' on unselectable dirs.

P3: /workspace set stored any string client-side and the chat route silently
dropped rejected values, so the pill could claim a confinement that was not
in effect. New admin-gated /api/workspace/vet validates manual paths before
they persist (canonical path returned), and when a posted workspace is
rejected at send time the stream emits workspace_rejected so the client
clears the stored value and toasts instead of continuing silently.

* fix(workspace): check caller privilege before vetting the posted workspace

Review finding: /api/chat_stream called vet_workspace() on the posted value
for every caller and emitted workspace_rejected on failure, so a non-admin
who can chat but cannot use file/shell tools could distinguish existing
directories from missing/file/sensitive/root paths by whether the event
appeared. The resolution now lives in _resolve_request_workspace, which
drops the submitted value uniformly for non-admin callers, with no vetting
and no event, before the path ever touches the filesystem. Admin and
single-user behavior is unchanged. Test pins that valid and invalid paths
are indistinguishable for a non-admin and that vet_workspace is never
invoked for them.
This commit is contained in:
Kenny Van de Maele
2026-06-11 18:17:54 +02:00
committed by GitHub
parent 95c54ac3cb
commit 620fdd0859
19 changed files with 955 additions and 71 deletions
+43
View File
@@ -17,6 +17,7 @@ import chatRenderer from './chatRenderer.js';
import spinnerModule from './spinner.js';
import themeModule from './theme.js';
import documentModule from './document.js';
import workspaceModule from './workspace.js';
import settingsModule from './settings.js';
import cookbookModule from './cookbook.js';
import { EVAL_PROMPTS } from './compare/index.js';
@@ -1229,6 +1230,40 @@ async function _cmdToggleDoc(args, ctx) {
return true;
}
// Workspace: confine the agent's file/shell tools to a folder. Not a boolean -
// show / set <path> / clear / pick (open the directory browser).
async function _cmdWorkspace(args, ctx) {
const sub = (args[0] || '').toLowerCase();
const rest = args.slice(1).join(' ').trim();
const cur = workspaceModule.getWorkspace();
if (!sub || sub === 'show' || sub === 'status' || sub === 'info') {
slashReply(cur ? `Workspace: <code>${uiModule.esc(cur)}</code>` : 'No workspace set. <code>/workspace pick</code> or <code>/workspace set /path</code>.');
return true;
}
if (sub === 'set' || sub === 'cd' || sub === 'use') {
if (!rest) { slashReply('Usage: <code>/workspace set /absolute/path</code>'); return true; }
// Validate server-side before persisting so the pill never claims a
// workspace the backend will refuse to bind (typo, file path, deleted
// folder, sensitive dir, filesystem root).
workspaceModule.vetAndSetWorkspace(rest).then(({ ok, path }) => {
if (ok) slashReply(`Workspace set: <code>${uiModule.esc(path)}</code>`);
else slashReply(`Not a usable workspace folder: <code>${uiModule.esc(rest)}</code>. It must be an existing directory, not a filesystem root or sensitive path.`);
});
return true;
}
if (sub === 'clear' || sub === 'off' || sub === 'none' || sub === 'unset') {
workspaceModule.clearWorkspace();
slashReply('Workspace cleared.');
return true;
}
if (sub === 'pick' || sub === 'browse' || sub === 'open') {
workspaceModule.openWorkspaceBrowser();
return true;
}
slashReply('Usage: <code>/workspace</code> · <code>set /path</code> · <code>clear</code> · <code>pick</code>');
return true;
}
async function _cmdToggleShow(args, ctx) {
const name = (args[0] || '').toLowerCase();
const val = (args[1] || '').toLowerCase();
@@ -5731,6 +5766,14 @@ const COMMANDS = {
'_show': { handler: _cmdToggleShow, alias: [], help: 'Show all toggle states', usage: '/toggle' }
}
},
workspace: {
alias: ['ws'],
category: 'Agent',
help: 'Set the folder the agent works in',
handler: _cmdWorkspace,
noUserBubble: true,
usage: '/workspace [set <path> | clear | pick]',
},
memory: {
alias: ['m'],
category: 'Memory',