mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
fix: harden sync_back — PID-suffix temp path, size cap, lifecycle guards
Follow-ups on top of kshitijk4poor's cherry-picked salvage of PR #8018: tools/environments/daytona.py - PID-suffix /tmp/.hermes_sync.<pid>.tar so concurrent sync_back calls against the same sandbox don't collide on the remote temp path - Move sync_back() inside the cleanup lock and after the _sandbox-None guard, with its own try/except. Previously a no-op cleanup (sandbox already cleared) still fired sync_back → 3-attempt retry storm against a nil sandbox (~6s of sleep). Now short-circuits cleanly. tools/environments/file_sync.py - Add _SYNC_BACK_MAX_BYTES (2 GiB) defensive cap: refuse to extract a tar larger than the limit. Protects against runaway sandboxes producing arbitrary-size archives. - Add 'nothing previously pushed' guard at the top of sync_back(). If _pushed_hashes and _synced_files are both empty, the FileSyncManager was never initialized from the host side — there is nothing coherent to sync back. Skips the retry/backoff machinery on uninitialized managers and eliminates test-suite slowdown from pre-existing cleanup tests that don't mock the sync layer. tests/tools/test_file_sync_back.py - Update _make_manager helper to seed a _pushed_hashes entry by default so sync_back() exercises its real path. A seed_pushed_state=False opt-out is available for noop-path tests. - Add TestSyncBackSizeCap with positive and negative coverage of the new cap. tests/tools/test_sync_back_backends.py - Update Daytona bulk download test to assert the PID-suffixed path pattern instead of the fixed /tmp/.hermes_sync.tar.
This commit is contained in:
parent
d64446e315
commit
7fd508979e
4 changed files with 113 additions and 13 deletions
|
|
@ -95,6 +95,7 @@ def _sha256_file(path: str) -> str:
|
|||
|
||||
_SYNC_BACK_MAX_RETRIES = 3
|
||||
_SYNC_BACK_BACKOFF = (2, 4, 8) # seconds between retries
|
||||
_SYNC_BACK_MAX_BYTES = 2 * 1024 * 1024 * 1024 # 2 GiB — refuse to extract larger tars
|
||||
|
||||
|
||||
class FileSyncManager:
|
||||
|
|
@ -219,6 +220,13 @@ class FileSyncManager:
|
|||
if self._bulk_download_fn is None:
|
||||
return
|
||||
|
||||
# Nothing was ever committed through this manager — the initial
|
||||
# push failed or never ran. Skip sync_back to avoid retry storms
|
||||
# against an uninitialized remote .hermes/ directory.
|
||||
if not self._pushed_hashes and not self._synced_files:
|
||||
logger.debug("sync_back: no prior push state — skipping")
|
||||
return
|
||||
|
||||
lock_path = (hermes_home or get_hermes_home()) / ".sync.lock"
|
||||
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
|
@ -292,6 +300,19 @@ class FileSyncManager:
|
|||
with tempfile.NamedTemporaryFile(suffix=".tar") as tf:
|
||||
self._bulk_download_fn(Path(tf.name))
|
||||
|
||||
# Defensive size cap: a misbehaving sandbox could produce an
|
||||
# arbitrarily large tar. Refuse to extract if it exceeds the cap.
|
||||
try:
|
||||
tar_size = os.path.getsize(tf.name)
|
||||
except OSError:
|
||||
tar_size = 0
|
||||
if tar_size > _SYNC_BACK_MAX_BYTES:
|
||||
logger.warning(
|
||||
"sync_back: remote tar is %d bytes (cap %d) — skipping extraction",
|
||||
tar_size, _SYNC_BACK_MAX_BYTES,
|
||||
)
|
||||
return
|
||||
|
||||
with tempfile.TemporaryDirectory(prefix="hermes-sync-back-") as staging:
|
||||
with tarfile.open(tf.name) as tar:
|
||||
tar.extractall(staging, filter="data")
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue