mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-06-17 10:15:27 -04:00
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:
committed by
GitHub
parent
95c54ac3cb
commit
620fdd0859
@@ -62,6 +62,33 @@ def _stream_set(session_id: str, **fields) -> None:
|
||||
rec.update(fields)
|
||||
|
||||
|
||||
def _resolve_request_workspace(request, raw_value) -> tuple:
|
||||
"""Resolve the posted workspace for this request: (workspace, rejected).
|
||||
|
||||
Privilege is checked BEFORE the path ever touches the filesystem. Only
|
||||
admin/single-user callers can use the workspace-backed file/shell tools,
|
||||
so only they get vet_workspace() and the workspace_rejected signal. For
|
||||
any other caller the submitted value is dropped uniformly, with no vetting
|
||||
and no event: otherwise the presence/absence of workspace_rejected would
|
||||
let a non-admin chat caller probe which host paths exist.
|
||||
|
||||
vet_workspace rejects non-directories, sensitive roots (.ssh, .gnupg,
|
||||
...), and filesystem roots; on rejection there is no confinement and the
|
||||
default tool-path allowlist applies. The rejected value is surfaced so the
|
||||
stream can tell an admin client (which believes a workspace is active)
|
||||
that it was dropped.
|
||||
"""
|
||||
requested = (raw_value or "").strip()
|
||||
if not requested:
|
||||
return "", ""
|
||||
from src.tool_security import owner_is_admin_or_single_user
|
||||
if not owner_is_admin_or_single_user(get_current_user(request)):
|
||||
return "", ""
|
||||
from src.tool_execution import vet_workspace
|
||||
workspace = vet_workspace(requested) or ""
|
||||
return workspace, (requested if not workspace else "")
|
||||
|
||||
|
||||
def _session_url_matches_endpoint(session_url: str, endpoint_base: str) -> bool:
|
||||
if not session_url or not endpoint_base:
|
||||
return False
|
||||
@@ -457,6 +484,10 @@ def setup_chat_routes(
|
||||
# manual form posts that still send plan_mode=true.
|
||||
plan_mode = False
|
||||
chat_mode = str(form_data.get("mode", "")).lower() # 'chat' or 'agent'
|
||||
# Workspace: confine the agent's file/shell tools to this folder.
|
||||
workspace, workspace_rejected = _resolve_request_workspace(
|
||||
request, form_data.get("workspace")
|
||||
)
|
||||
# Plan mode is a modifier on agent mode — it only makes sense with tools.
|
||||
if plan_mode:
|
||||
chat_mode = "agent"
|
||||
@@ -761,6 +792,13 @@ def setup_chat_routes(
|
||||
# Register active stream for partial-save safety net
|
||||
_active_streams[session] = {"status": "streaming", "partial": "", "query": message, "is_research": effective_do_research, "mode": _effective_mode}
|
||||
|
||||
# The client sent a workspace the server refused to bind (deleted
|
||||
# folder, file path, sensitive dir, filesystem root). Tell it up
|
||||
# front so the UI can clear the pill instead of displaying a
|
||||
# confinement that is not actually in effect.
|
||||
if workspace_rejected:
|
||||
yield f"data: {json.dumps({'type': 'workspace_rejected', 'data': {'path': workspace_rejected}})}\n\n"
|
||||
|
||||
if ctx.preprocessed.attachment_meta:
|
||||
yield f"data: {json.dumps({'type': 'attachments', 'data': ctx.preprocessed.attachment_meta})}\n\n"
|
||||
|
||||
@@ -1138,6 +1176,7 @@ def setup_chat_routes(
|
||||
fallbacks=_fallback_candidates,
|
||||
plan_mode=plan_mode,
|
||||
approved_plan=approved_plan or None,
|
||||
workspace=workspace or None,
|
||||
):
|
||||
if chunk.startswith("data: ") and not chunk.startswith("data: [DONE]"):
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user