GLOBTIMEOUT does not bound wall-clock time — tool blocks until the runaway glob finishes…
- User
GLOB_TIMEOUTdoes not bound wall-clock time — tool blocks until the runaway glob finishesSubmission checklist
- This is a bug, not a usage question.
- I added a clear and descriptive title.
- I searched existing issues and didn't find this.
- I can reproduce this with the latest released version.
- I included a minimal reproducible example and steps to reproduce.
Area (Required)
- deepagents (SDK)
- cli
- code
- talon
- acp
- evals
- harbor
- daytona
- modal
- quickjs
- runloop
- langsmith-sandbox
- Other / not sure / general
Related Issues / PRs
No response
Reproduction Steps / Example Code (Python)
import time from unittest.mock import patch from deepagents.backends import StateBackend from deepagents.middleware import filesystem as fs_mw from deepagents.middleware.filesystem import FilesystemMiddleware class FakeRuntime: tool_call_id = "demo" state = {"files": {}} store = None context = None stream_writer = None config = {} backend = StateBackend() real_glob = backend.glob middleware = FilesystemMiddleware(backend=backend) glob_tool = next(t for t in middleware.tools if t.name == "glob") def slow_glob(*args, **kwargs): time.sleep(3) # a glob that takes 3s (stand-in for a huge tree / slow mount) return real_glob("*.none") with ( patch.object(fs_mw, "GLOB_TIMEOUT", 0.5), # 20s in production; shortened for the repro patch.object(backend, "glob", side_effect=slow_glob), ): start = time.monotonic() msg = glob_tool.invoke({"pattern": "**/*", "runtime": FakeRuntime()}) print(f"returned after {time.monotonic() - start:.2f}s: {msg.content!r}") # Expected: returns after ~0.5s (the timeout) # Actual: returns after ~3.0s -- the full duration of the "timed out" globError Message and Stack Trace (if applicable)
returned after 3.01s: 'Error: glob timed out after 0.5s. Try a more specific pattern or a narrower path.'Description
- The synchronous
globtool created byFilesystemMiddlewareenforcesGLOB_TIMEOUT(20s) by running the backend glob on a worker thread:future.result(timeout=GLOB_TIMEOUT)inside awith concurrent.futures.ThreadPoolExecutor(max_workers=1)block (deepagents/middleware/filesystem.py,sync_glob). - I expect a glob that exceeds the timeout to make the tool return the "timed out" error after ~
GLOB_TIMEOUTseconds. - Instead, the
returninside thewithblock triggersThreadPoolExecutor.__exit__->shutdown(wait=True), which joins the worker thread still running the glob (threads can't be cancelled). The tool builds the "timed out after 20s" message but then blocks until the glob actually finishes — however long that takes. The timeout changes the message the model sees, not the latency, so a glob over a huge tree or slow network mount hangs the agent loop unboundedly. - Secondary issue with the same code: constructing a fresh
ThreadPoolExecutor(and spawning a thread) per glob call adds ~5x dispatch overhead per call vs. reusing a shared executor. - The async variant (
async_glob) is not affected —asyncio.wait_forcancels and returns immediately.
Environment / System Info
OS: macOS 14 (Darwin 23.6.0, arm64) Python: 3.13.5 deepagents: 0.6.8 (also reproducible on main @ 676abecf)
Interface
No new interfaces are introduced.
- Assistant
I’ll trace the SDK filesystem middleware and its tests, then implement a bounded sync timeout with regression coverage for both latency and normal/error behavior.
- Assistant
The defect is exactly at executor cleanup: the timeout is raised on schedule, but context-manager shutdown immediately waits for the worker. I’m checking repository conventions and Python shutdown implications before choosing the shared execution primitive, since abandoned work must not reintroduce blocking during later calls or process exit.
- Assistant
The regression now returns in roughly the configured timeout, while the abandoned backend call finishes independently. The focused sync glob tests pass; I’m running lint/type checks and the broader filesystem middleware suite next, including checking that the shared executor doesn’t alter context propagation or result handling.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- fable-5Compare side by side →
- fable-5Compare side by side →