ISSUE DESCRIPTION GLOBTIMEOUT does not bound wall-clock time — tool blocks until the…
- User
ISSUE DESCRIPTION
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)
ADDITIONAL ADVICE
Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use
git checkout <file>to restore the file to its original state. You can also reset all changes in the repository usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto get the changes that need to be submitted.CHECKLIST
Before submitting your solution, please go over the following checklist and make sure you've done everything:
- If an error was reported in the issue description, I have successfully reproduced it.
- If an error was reported in the issue description, I have confirmed that my fix resolves the error.
- I have thought about edge cases and made sure my fix handles them as well.
- I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.
Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!
(Current directory: /deepagents, current file: none) bash-$
- Assistant
I’ll inspect the filesystem middleware and its tests, reproduce the executor shutdown behavior, then implement a bounded-return design that avoids waiting on timed-out worker threads. I’ll preserve existing semantics, add no repository tests per instruction, and run the relevant existing test suite plus a temporary verification script.
- Assistant
The initial path assumption was wrong—the repository layout does not have
deepagents/middleware/filesystem.pyat that location. I’ll locate the package and then inspect the implementation and tests from the actual paths. - Assistant
The bug is exactly in
sync_glob: thewith ThreadPoolExecutor(...)context manager waits during exit afterfuture.resulttimes out. I’ll replace the per-call executor with a module-level shared executor, submit the context-wrapped backend call, and deliberately not shut it down in the tool path. This lets the caller return at the timeout while the un-cancellable backend operation finishes in the background, and also removes per-call thread creation. - Assistant
The code change is in place. The first test run could not import the package because dependencies are not on the current shell’s
PYTHONPATH; the repository includes a package virtual environment, so I’ll rerun using that environment and separately execute a focused timing check. I’ll also inspect formatting and the exact diff before finalizing. - Assistant
The focused reproduction now returns in about 0.2 seconds for a 2-second backend call, confirming the wall-clock fix. I’ll make one small robustness improvement: attempt
future.cancel()on timeout so queued (not-yet-started) globs do not run unnecessarily; running backend calls remain uncancellable but no longer block the tool. Then I’ll run available static checks and inspect status.
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
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →