* fix(sandbox): bound remaining shell session cleanup requests
release_command_scope(), close()'s scoped-session drain, and close()'s recovery-session cleanup called shell.cleanup_session() without a request budget, so a stalled cleanup could hold the thread-key serializer, scoped.lock, or the sandbox lock for the SDK's default transport budget. Pass the existing _bounded_cleanup_request_options() (5s, max_retries=0) at those three sites; _cleanup_session_best_effort() and its swallow-and-log contract are unchanged, as are create_session and list_dir lifetimes.
* fix(sandbox): bound AIO list_dir with a directory deadline
Give AioSandbox.list_dir its own 60s directory deadline with a 65s no-retry
host envelope, independent of bash_command_timeout. Preserve #5634's
shell-generation selection: list_dir runs on the current recovery session once
the implicit shell is fenced, and an ambiguous list_dir outcome - transport
timeout or an ambiguous returned status - fences whichever generation actually
executed the request, dropping local recovery ownership and attempting bounded
best-effort cleanup instead of leaving that session reusable. hard_timeout
remains definite termination and keeps the targeted session reusable. Only
completed/None results are parsed, so a partial find is never returned as a
complete listing.
Session creation RPC lifetime remains out of scope.
* fix(sandbox): recover sessions after transport failures
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(sandbox): enforce AIO shell command timeouts
Map Sandbox.execute_command(timeout=T) onto the AIO legacy shell as a server-side hard_timeout=T plus a bounded host request (ceil(T+5)s, max_retries=0), preserve and render the upstream status (hard_timeout -> terminated + Exit Code: 124; no_change_timeout -> may still be running), keep no_change_timeout from preempting hard_timeout, and restrict ErrorObservation replay to completed results.
* fix(sandbox): contain ambiguous AIO command outcomes
Treat a transport timeout and statuses terminated/no_change_timeout/unknown as ambiguous: never replay the current command, fence the scoped or recovery session generation with bounded best-effort cleanup, and never adopt a replacement session for those statuses. hard_timeout and completed keep the session reusable. Align the env-bearing bash.exec path with the same contract and make its retry result authoritative.
* fix(sandbox): wire AIO command timeout from provider config
Restore bash_tool's non-local behaviour (other providers keep their own defaults) and let AioSandboxProvider read sandbox.bash_command_timeout as the sandbox's default_command_timeout at every construction site, with explicit per-call timeouts still winning. Widen the config field to float with allow_inf_nan=False and read the provider value with the module fallback so partial-config providers keep working.
* docs(sandbox): document AIO command timeout semantics
Document the provider-scoped deadline (LocalSandbox/AioSandbox/OpenSandbox wire it; other providers keep their defaults), the semver-vs-frozen-:latest image behaviour, the no-replay guarantees, and trim the sandbox guidance back under its size budget.
* docs(sandbox): scope the wedge-resistance claim to command requests
willem-bd's review on #5634 reproduced that list_dir and both create_session call sites still make unbounded SDK requests while holding the same sandbox lock, so the guide must not read as if every AIO request is bounded. State that the bounded T+5s host wait applies to command requests and name session-creation and file/list RPCs as not covered; bounding those remains a separate operation-deadline/control-plane follow-up.
* fix(sandbox): make list_dir honor the shell generation fence
list_dir previously always targeted the implicit persistent shell, so after an ambiguous command outcome fenced that generation (#5634) a listing could re-enter it. Route default-shell target selection through _ensure_default_shell_session_id so both execute_command and list_dir reuse the explicit recovery session, creating one only when the implicit shell is fenced. No list_dir deadline, hard_timeout, request budget, retry, or status semantics are added; those remain scoped to #5644.
* fix(sandbox): force UTF-8 console for PowerShell so CJK output is not garbled
LocalSandbox captures PowerShell output through a UTF-8 pipe reader
(errors=replace), but Windows PowerShell 5.1 writes console output in
the legacy OEM codepage (GBK on zh-CN Windows) unless told otherwise,
so every CJK character in tool output arrives as mojibake and the
decode never raises. Prepend a UTF-8 preamble
([Console]::InputEncoding/[Console]::OutputEncoding/$OutputEncoding)
to the -Command payload so both directions of the console are UTF-8
before the user command runs.
* fix(sandbox): pair PowerShell UTF-8 capture and guard console setup
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(sandbox): report truncated remote glob and grep results
BoxLite, Tenki, E2B, and OpenSandbox run find/grep in the sandbox, cap
the raw output with `| head`, and then filter those lines in Python:
ignored directories such as node_modules are dropped and grep's glob
scope is applied. They reported truncated only when max_results matches
survived the filter. When the capped lines were mostly filtered out, a
search with real matches past the cap came back short or empty with
truncated=False, and glob_tool/grep_tool rendered it as "No files
matched" / "No matches found". With the default max_results=200 and
1,200 files under node_modules, glob("**/*.py") reported no matches for
a workspace that has src/app.py.
remote_search_command now lets one line past its limit through, and
parse_remote_search_output(..., limit=) returns RemoteSearchOutput(text,
truncated): the first `limit` lines and whether the extra line arrived.
Exactly `limit` lines stays a complete result. Each provider passes the
cap it already computed to both calls and returns that truncated from
glob and grep when fewer than max_results results survive filtering.
The glob and grep tools now describe an empty truncated result as
incomplete instead of reporting no matches, which also covers AIO grep's
forwarded truncated flag. Sandbox.glob/grep document truncated as "the
matches may be incomplete".
* docs(changelog): reference #5427 in the remote search truncation entry
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(sandbox): mask every host path in a colon-joined list
Host-to-virtual output masking matched a host root and then consumed the
path tail up to whitespace or shell punctuation, but not `:`. A
`:`-joined list such as $PATH or $PYTHONPATH was therefore swallowed into
the first match's tail, and scanning resumed after it, so every later
entry under the same root reached the model as a raw host path. The regex
matcher (process-stable skill roots) and the direct scanner (per-thread
roots, LocalSandbox) shared the gap. Each redundant masking pass --
separator variants, the realpath spelling, the /mnt/user-data root
mapping, LocalSandbox's own reverse resolution -- happened to recover one
entry, which hid the leak for short lists: bash output leaked from the
fourth entry, single-pass consumers from the third.
The shared tail in path_patterns.py now ends at `:` in both matchers.
`;`, the Windows list separator, already ended it. A `:` inside one path
(grep -n output, a file name) only shortens the match; the remaining text
is copied through verbatim.
Shortening the match exposed a second leak. LocalSandbox reverse
resolution realpaths the matched path and returned that realpath when no
mount contained it, so a symlink inside a mount whose target lies outside
every mount was shown as the target's host path. grep -n lines used to
hide this only because the whole line resolved as one nonexistent file;
whitespace-terminated output and LocalSandbox.glob results already leaked
it on main. Reverse resolution now falls back to the link's own spelling,
normalized so `mount/../x` does not pass, before giving up. A symlink into
another mount still reports that mount's path.
* docs(changelog): reference #5418 in the colon-joined path masking entry
* docs(changelog): split the #5418 and #5419 entries fused by the merge
Resolving the CHANGELOG conflict when main was merged in dropped the
opener of the #5419 entry, so the BoxLite grep fix continued inside this
PR's bullet in both CHANGELOG.md and CHANGELOG_zh.md. Restore it as its
own bullet; the #5419 entry is byte-identical to main again.
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(sandbox): scope BoxLite grep globs to the search root
BoxliteBox.grep omits grep --include for busybox portability and applies
the glob in Python, but it kept only the glob's last path segment and
matched it against each file's basename. A scoped pattern therefore lost
its directory part: grep(glob="src/*.js") returned every .js file in the
tree, including vendor/ and nested src/ subdirectories that glob() with
the same pattern excludes.
The glob now goes through path_matches against the path relative to the
search root, with the file's basename when the root is a single file --
the same scope glob() uses and the one Tenki, E2B, OpenSandbox, AIO and
LocalSandbox already enforce. Like those providers, an empty glob is now
passed to path_matches instead of being treated as no filter.
* docs(changelog): reference #5419 in the BoxLite grep glob scope entry
* fix(sandbox): stop remote grep/glob from reporting failures as no matches
E2B, OpenSandbox, BoxLite and Tenki ran grep/find behind `2>/dev/null | head`, so a missing search root, a missing grep/find binary or an unreadable tree exited 0 with empty stdout and the tools reported "No matches found". Wrap the search in sandbox/remote_search.py, which checks the root first and records the search's own status after head, as remote_list_dir does for list_dir: a missing root raises FileNotFoundError, a failed search raises OSError, and a genuine no-match still returns []. glob's find gains -H for symlinked roots, OpenSandbox's BusyBox fallback keeps the primary grep status, and E2B no longer swallows client errors. Regression tests run each provider's real command in a local POSIX sh.
Fixes#5376
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(sandbox): fail remote grep/glob on partial traversal errors
grep 2 / find 1 after some results were printed (an unreadable file or
subdirectory) were returned as a complete search. Callers have no
partial-result channel, and #5376 asks for permission and command
failures to raise, so these statuses now raise OSError like any other
failure. Only grep 0/1/141 and find 0/141 pass.
The error for grep 2 / find 1 says that some files or directories could
not be read and asks for a narrower path, so the agent can retry instead
of giving up.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
* fix(sandbox): stop list_dir from reporting failures as empty
Remote providers swallowed find/client errors as [] and 2>/dev/null
missing paths as empty stdout. ls_tool then told the agent the
directory was (empty). Raise OSError/FileNotFoundError instead so
the tool returns Error.
* fix(sandbox): list_dir raises on missing local paths and uses find -H
Empty stdout is not a missing path when find's start point is a
symlink (E2B /mnt/acp-workspace). Dereference only the start point
with find -H. LocalSandbox now raises FileNotFoundError for a
non-directory root, matching remote providers. AIO maps a missing
result.data to OSError rather than FileNotFoundError.
* fix(sandbox): group AIO list_dir find type predicates
Without parentheses, find PATH -maxdepth N -type f -o -type d applies
-type d without maxdepth and can drop files from the listing.
* fix(sandbox): distinguish list_dir command failure from missing path
Tenki, Boxlite, and OpenSandbox treated any empty find stdout as
FileNotFoundError, so a missing find binary (exit 127) or SDK error
looked like a missing directory. Raise OSError when find status is
outside (0, 1); keep FileNotFoundError for the find-ran-but-empty case.
* fix(sandbox): apply list_dir exit-status contract to AIO and E2B
Same gap as Tenki/Boxlite/OpenSandbox: empty find stdout with exit 127
was FileNotFoundError. Raise OSError when the status is outside (0, 1).
* fix(sandbox): classify list_dir by find status not head status
find | head under sh -lc reports head's exit code, so a missing find
binary (127) became FileNotFoundError. Record find's own status after
the bounded listing, treat SIGPIPE 141 as truncation success, and add
a shell-level regression test.
* test(auth): include projects permissions in /me contract pins
#5265 added projects:read/write/delete to the registered route set.
The /auth/me tests still pinned the pre-projects list, so CI failed
after merging main.
* fix(sandbox): do not treat missing list_dir marker as success
The generated script ended on `rm -f`, so process status was 0/1 even
when find's marker never landed. Both codes are in _FIND_OK, and the
parser fallback then classified an empty listing as FileNotFoundError —
the 127 misclassification this helper was meant to close.
Exit with find's status (126 if unknown). A missing marker is now
OSError unless the process status is already a non-OK failure.
* test(sandbox): emit list_dir status marker in provider fixtures
Parser now requires __DF_FIND_STATUS__ and refuses marker-less stdout.
Update AIO/Boxlite/E2B stubs and OpenSandbox/Tenki find fakes so listings
carry :0 and missing paths carry :1 with matching exit codes.
* style(sandbox): format list dir test fixture
* style(sandbox): format remote list dir helper
* docs(sandbox): keep guidance within the tested size budget
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(deps): depend on renamed tenki package instead of tenki-sandbox
tenki-sandbox has been removed from PyPI and republished as tenki. Its old wheel URL still resolves, so existing lockfiles keep installing and the breakage is invisible to anyone with a warm lock; any fresh resolution fails with 'tenki-sandbox was not found in the package registry'.
tenki 1.0.2 still ships the tenki_sandbox module, so the imports in community/tenki/provider.py and sandbox.py are unchanged.
Fixes#5081
* fix(tenki): point install guidance at the renamed distribution
The rename to `tenki` left the user-facing remediation still naming the
removed package. `_import_client` raised "pip install tenki-sandbox" on the
missing-extra path — the exact instruction this change proves now 404s on
PyPI, handed to the user at the exact moment they need it to work.
Update that message and the remaining `tenki-sandbox` references in the
provider, sandbox adapter, README, sandbox AGENTS.md and the test docstring.
The imported module stays `tenki_sandbox`, so the distribution and module
names now differ; each mention says so rather than just swapping the string.
No behavior change beyond the error text.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(tenki): migrate the provider to the 1.x workspace-only API
Renaming the dependency was not enough. tenki 1.0.2 keeps the tenki_sandbox
module name but not its contract: Client.create dropped project_id and has no
**kwargs to absorb it, and IdentityWorkspace no longer carries `projects`
(the attribute is gone from the package entirely). Both configuration paths
therefore failed before a sandbox could be created — explicit project scope
raised TypeError, and automatic scope raised AttributeError walking
workspace.projects.
Scope is now the workspace alone. _resolve_scope returns a single workspace id,
auto-selecting when the account has exactly one, and project_id is gone from
create_kwargs and from the documented config surface.
A stale project_id in config.yaml warns rather than fails. SandboxConfig is
extra="allow", so simply not reading the key would leave it scoping nothing
with no signal; it also used to short-circuit the identity lookup, so operators
with more than one workspace need to know they must now set workspace_id.
The suite passed against the broken provider because the fake client took
**kwargs and swallowed the project_id the real SDK rejects. The double now
mirrors 1.0.2 — keyword-only, no **kwargs — so an unexpected argument is a
TypeError in tests exactly as it is against the SDK. Reintroducing the old
create call fails 20 tests; before this change it failed none.
Verified against the exact locked wheels: every other kwarg the provider
passes (name, workspace_id, sticky, wait, max_duration, image, cpu_cores,
memory_mb, env) and every SDK surface it touches (who_am_i, Identity.workspaces,
wait_ready, exec, close, the fs API, the four terminal exception classes) is
unchanged in 1.0.2.
Reported by willem-bd in review.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs(config): drop sandbox.project_id from the Tenki example
The canonical example still documented project_id as a supported optional key
after the provider stopped honouring it, so an operator following it could set
the key, get no scope from it, and hit a workspace-resolution failure with
nothing in the example to explain why.
Replaced with a migration note rather than a silent deletion: someone upgrading
already has the key in their config.yaml and needs to know it is inert now and
that workspace_id is what scopes a sandbox on Tenki 1.x.
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Aniket Wagh <aniketwaghh@users.noreply.github.com>
* feat(sandbox): share sandbox identity derivation and acquire serialization (#4741)
Remote providers (AIO, E2B, BoxLite, Tenki, OpenSandbox) each inlined the
same sha256(user:thread)[:16] sandbox-id expression and kept per-scope lock
dicts that grew unboundedly until shutdown. This extracts both mechanisms
into shared components without changing provider lifecycle, ids, capacity
semantics, or public tool behavior:
- sandbox/identity.py: keyword-only derive_sandbox_scope_token (byte-pinned
compatibility contract) + is_sandbox_scope_token; per-provider golden
vectors pin current behavior including BoxLite's raw-None quirk and each
provider's private user_id resolution.
- sandbox/acquire_serialization.py: AcquireSerializer — per-key lock table
with holder/waiter refcount reclamation, bounded dedicated executor
(async waits off both the event loop and the default executor),
worker-owned cancellation cleanup (no event-loop callback dependency), idempotent close().
- Each provider adopts both components; AIO/E2B key by (user_id, thread_id)
with acquire and (E2B) release serialized; BoxLite/Tenki/OpenSandbox key
by derived sandbox id and offload the whole sync acquire to the
serializer's executor so a cancelled awaiter cannot overlap a retried
same-scope body (leaked-remote-VM regression caught in review).
- thread_id=None acquires stay unserialized; provider shutdown()/reset()
close the serializer; E2B capacity/ledger/reconciliation and AIO
ownership/flock machinery untouched.
- blocking-IO anchor proves contended OpenSandbox acquire_async stays off
the event loop (teeth verified red/green); AGENTS.md documents the
shared components.
* refactor(sandbox): address review on acquire serialization (#5089)
- Replace unreachable checkin branch with an assertion: run() returns
False only after abandon(), which the except handler always re-raises;
the old _checkin would have double-decremented the refcount.
- Document the task.cancelling() == 0 assumption in hold_async.
- Drop unused thread_id/user_id kwargs from BoxLite and Tenki
_acquire_scope_locked (OpenSandbox still forwards them).
* fix(sandbox): preserve request ContextVars in acquire executor bridge (#5089)
loop.run_in_executor() does not copy contextvars, unlike the inherited
SandboxProvider.acquire_async() which used asyncio.to_thread(). The
BoxLite/OpenSandbox/Tenki acquire_async bridges introduced in this PR
therefore dropped the request trace id (logged as trace_id=-).
Add AcquireSerializer.run_on_executor(), which copies the calling
context and runs the callable through ctx.run, and route all three
providers through it. Add regression tests binding request_trace_context
and verifying the worker thread observes it.
* Preserve Windows CLI compatibility for local sandbox commands
MSYS path conversion must remain disabled for DeerFlow virtual paths, but applying a blanket environment override to every POSIX command breaks host-native CLI shims on Windows. Limit MSYS argument-conversion exclusions to safe non-root virtual path prefixes, omit values that would broaden the exclusion pattern, and document the contract.
Constraint: Preserve the virtual-path protection introduced by #2765/#2766
Rejected: Disable MSYS conversion for every command | breaks Windows CLI shims
Rejected: Toggle blanket conversion only for commands containing virtual paths | host CLIs can receive virtual-path arguments and still need normal conversion for their own paths
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep regression coverage for virtual-path arguments, root mounts, and host-native CLI launchers
Tested: test_local_sandbox_encoding.py (12 passed); related sandbox suite (197 passed, 8 skipped, 7 failures matching origin/main); ruff check; ruff format --check; git diff --check; direct LocalSandbox CLI and virtual-path smoke tests
Not-tested: Full offline suite completion; stopped at 6% after unrelated Windows and optional-runtime failures
Related: #2765
Related: #2766
* Keep MSYS regression tests portable across CI operating systems
The Windows-shell environment tests patched os.name to nt while mounting Windows-specific paths. On Linux and macOS, pathlib then attempted to construct WindowsPath during command resolution or output masking, so the backend merge gate failed before exercising the environment contract. Stub the exclusion boundary in execute-command tests and retain mapping-specific filtering coverage in the helper test.
Constraint: Backend unit tests run on Linux, while the behavior under test is Windows-only
Rejected: Skip the tests outside Windows | would remove CI coverage of the environment contract
Rejected: Patch pathlib internals | couples tests to implementation details and hides the platform boundary
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep OS-specific subprocess assertions independent from host-path resolution
Tested: test_local_sandbox_encoding.py (12 passed); ruff check; ruff format --check; git diff --check
Not-tested: Linux runner execution locally because Docker Desktop is unavailable and WSL cannot access this linked worktree
Related: #5003
Related: https://github.com/bytedance/deer-flow/pullrequestreview-5013380238
Sandbox is an execution environment, not a named resource: multiple tools
(bash, read_file, write_file, glob, grep, ...) depend on it, all funneled
through ensure_sandbox_initialized / ensure_sandbox_initialized_async. Gate
the single acquisition entry point (single source of truth) instead of
maintaining a sandbox-tool-name set in middleware:
- authorize_sandbox_execution helper (authz/sandbox_authz.py) checks
authorize("sandbox", "execute", target="*") — a binary judgment
(can this role use the sandbox at all); RBAC allow:"*"/true permits,
allow:[]/false denies.
- lazy path: ensure_sandbox_initialized (+ async) calls the gate before
provider.acquire.
- eager path: SandboxMiddleware.before_agent / abefore_agent call the gate
before _acquire_sandbox.
- deny raises SandboxAuthorizationError (SandboxError subclass) which
propagates through tool execution as a friendly ToolMessage (RFC §9:
'not a crash').
- authorization.enabled: false is a no-op everywhere; provider errors
follow fail_closed (deny) / fail_open (allow).
12 tests in tests/test_sandbox_authorization.py cover disabled/allow/deny/
deny-via-bool/no-policy-unrestricted/provider-error-fail-closed/open/
internal-caller + ensure_sandbox_initialized deny (never acquires) and
allow (acquires) integration paths.
* docs: govern agent guidance size
* refactor: split agent guidance by code scope
* Clarify virtual path handling in AGENTS.md
Updated the translation section to clarify the role of `LocalSandboxProvider` and the handling of virtual paths in the tool layer.
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
