Files
odysseus/src/agent_tools/subprocess_tools.py
T
Kenny Van de Maele 620fdd0859 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.
2026-06-11 18:17:54 +02:00

154 lines
5.3 KiB
Python

import asyncio
import sys
import time
import collections
from typing import Optional, Callable, Awaitable, Tuple, Dict
from src.constants import MAX_OUTPUT_CHARS
DEFAULT_BASH_TIMEOUT = 60 * 60 # 1 hour
DEFAULT_PYTHON_TIMEOUT = 60 * 60
PROGRESS_INTERVAL_S = 2.0
PROGRESS_TAIL_LINES = 12
async def _run_subprocess_streaming(
proc: asyncio.subprocess.Process,
*,
timeout: float,
progress_cb: Optional[Callable[[Dict], Awaitable[None]]] = None,
) -> Tuple[str, str, Optional[int], bool]:
started = time.time()
stdout_full: list[str] = []
stderr_full: list[str] = []
tail = collections.deque(maxlen=PROGRESS_TAIL_LINES)
async def _reader(stream, full_buf, label: str):
if stream is None:
return
while True:
line = await stream.readline()
if not line:
break
decoded = line.decode("utf-8", errors="replace").rstrip("\n")
full_buf.append(decoded)
if label == "err":
tail.append(f"! {decoded}")
else:
tail.append(decoded)
async def _progress_emitter():
await asyncio.sleep(PROGRESS_INTERVAL_S)
while True:
if progress_cb:
try:
await progress_cb({
"elapsed_s": round(time.time() - started, 1),
"tail": "\n".join(list(tail)),
})
except Exception:
pass
await asyncio.sleep(PROGRESS_INTERVAL_S)
rd_out = asyncio.create_task(_reader(proc.stdout, stdout_full, "out"))
rd_err = asyncio.create_task(_reader(proc.stderr, stderr_full, "err"))
prog_task = asyncio.create_task(_progress_emitter()) if progress_cb else None
timed_out = False
try:
await asyncio.wait_for(proc.wait(), timeout=timeout)
except asyncio.TimeoutError:
timed_out = True
try:
proc.kill()
except Exception:
pass
try:
await asyncio.wait_for(proc.wait(), timeout=2)
except Exception:
pass
except asyncio.CancelledError:
try:
proc.kill()
except Exception:
pass
try:
await asyncio.wait_for(proc.wait(), timeout=2)
except Exception:
pass
for t in (rd_out, rd_err):
t.cancel()
if prog_task is not None:
prog_task.cancel()
raise
finally:
if prog_task is not None and not prog_task.done():
prog_task.cancel()
try:
await prog_task
except (asyncio.CancelledError, Exception):
pass
for t in (rd_out, rd_err):
try:
await asyncio.wait_for(t, timeout=1)
except Exception:
pass
return (
"\n".join(stdout_full),
"\n".join(stderr_full),
proc.returncode,
timed_out,
)
class BashTool:
async def execute(self, content: str, ctx: dict) -> dict:
from src.tool_execution import agent_cwd, _truncate
progress_cb = ctx.get("progress_cb")
_subproc_env = ctx.get("subproc_env")
proc = await asyncio.create_subprocess_shell(
content,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
env=_subproc_env,
cwd=agent_cwd(),
)
stdout, stderr, rc, timed_out = await _run_subprocess_streaming(
proc,
timeout=DEFAULT_BASH_TIMEOUT,
progress_cb=progress_cb,
)
if timed_out:
return {"error": f"bash: timed out after {DEFAULT_BASH_TIMEOUT}s — process killed", "exit_code": 124, "stdout": _truncate(stdout, MAX_OUTPUT_CHARS), "stderr": _truncate(stderr, MAX_OUTPUT_CHARS)}
output = stdout.rstrip()
err = stderr.rstrip()
if err:
output = (output + "\nSTDERR: " + err).strip() if output else "STDERR: " + err
output = _truncate(output, MAX_OUTPUT_CHARS)
return {"output": output or "(no output)", "exit_code": rc or 0}
class PythonTool:
async def execute(self, content: str, ctx: dict) -> dict:
from src.tool_execution import agent_cwd, _truncate
progress_cb = ctx.get("progress_cb")
_subproc_env = ctx.get("subproc_env")
proc = await asyncio.create_subprocess_exec(
(sys.executable or "python"), "-I", "-c", content,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
env=_subproc_env,
cwd=agent_cwd(),
)
stdout, stderr, rc, timed_out = await _run_subprocess_streaming(
proc,
timeout=DEFAULT_PYTHON_TIMEOUT,
progress_cb=progress_cb,
)
if timed_out:
return {"error": f"python: timed out after {DEFAULT_PYTHON_TIMEOUT}s — process killed", "exit_code": 124, "stdout": _truncate(stdout, MAX_OUTPUT_CHARS), "stderr": _truncate(stderr, MAX_OUTPUT_CHARS)}
output = stdout.rstrip()
err = stderr.rstrip()
if err:
output = (output + "\nSTDERR: " + err).strip() if output else "STDERR: " + err
output = _truncate(output, MAX_OUTPUT_CHARS)
return {"output": output or "(no output)", "exit_code": rc or 0}