mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
d64446e315
Salvage of PR #8018 by @alt-glitch onto current main. On sandbox teardown, FileSyncManager now downloads the remote .hermes/ directory, diffs against SHA-256 hashes of what was originally pushed, and applies only changed files back to the host. Core (tools/environments/file_sync.py): - sync_back(): orchestrates download -> unpack -> diff -> apply with: - Retry with exponential backoff (3 attempts, 2s/4s/8s) - SIGINT trap + defer (prevents partial writes on Ctrl-C) - fcntl.flock serialization (concurrent gateway sandboxes) - Last-write-wins conflict resolution with warning - New remote files pulled back via _infer_host_path prefix matching Backends: - SSH: _ssh_bulk_download — tar cf - piped over SSH - Modal: _modal_bulk_download — exec tar cf - -> proc.stdout.read - Daytona: _daytona_bulk_download — exec tar cf -> SDK download_file - All three call sync_back() at the top of cleanup() Fixes applied during salvage (vs original PR #8018): | # | Issue | Fix | |---|-------|-----| | C1 | import fcntl unconditional — crashes Windows | try/except with fallback; _sync_back_locked skips locking when fcntl=None | | W1 | assert for runtime guard (stripped by -O) | Replaced with proper if/raise RuntimeError | | W2 | O(n*m) from _get_files_fn() called per file | Cache mapping once at start of _sync_back_impl, pass to resolve/infer | | W3 | Dead BulkDownloadFn imports in 3 backends | Removed unused imports | | W4 | Modal hardcodes root/.hermes, no explanation | Added docstring comment explaining Modal always runs as root | | S1 | SHA-256 computed for new files where pushed_hash=None | Skip hashing when pushed_hash is None (comparison always False) | | S2 | Daytona /tmp/.hermes_sync.tar never cleaned up | Added rm -f after download (best-effort) | Tests: 49 passing (17 new: _infer_host_path edge cases, SIGINT main/worker thread, Windows fcntl=None fallback, Daytona tar cleanup). Based on #8018 by @alt-glitch.
247 lines
8.7 KiB
Python
247 lines
8.7 KiB
Python
"""Daytona cloud execution environment.
|
|
|
|
Uses the Daytona Python SDK to run commands in cloud sandboxes.
|
|
Supports persistent sandboxes: when enabled, sandboxes are stopped on cleanup
|
|
and resumed on next creation, preserving the filesystem across sessions.
|
|
"""
|
|
|
|
import logging
|
|
import math
|
|
import shlex
|
|
import threading
|
|
from pathlib import Path
|
|
|
|
from tools.environments.base import (
|
|
BaseEnvironment,
|
|
_ThreadedProcessHandle,
|
|
)
|
|
from tools.environments.file_sync import (
|
|
FileSyncManager,
|
|
iter_sync_files,
|
|
quoted_mkdir_command,
|
|
quoted_rm_command,
|
|
unique_parent_dirs,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class DaytonaEnvironment(BaseEnvironment):
|
|
"""Daytona cloud sandbox execution backend.
|
|
|
|
Spawn-per-call via _ThreadedProcessHandle wrapping blocking SDK calls.
|
|
cancel_fn wired to sandbox.stop() for interrupt support.
|
|
Shell timeout wrapper preserved (SDK timeout unreliable).
|
|
"""
|
|
|
|
_stdin_mode = "heredoc"
|
|
|
|
def __init__(
|
|
self,
|
|
image: str,
|
|
cwd: str = "/home/daytona",
|
|
timeout: int = 60,
|
|
cpu: int = 1,
|
|
memory: int = 5120,
|
|
disk: int = 10240,
|
|
persistent_filesystem: bool = True,
|
|
task_id: str = "default",
|
|
):
|
|
requested_cwd = cwd
|
|
super().__init__(cwd=cwd, timeout=timeout)
|
|
|
|
from daytona import (
|
|
Daytona,
|
|
CreateSandboxFromImageParams,
|
|
DaytonaError,
|
|
Resources,
|
|
SandboxState,
|
|
)
|
|
|
|
self._persistent = persistent_filesystem
|
|
self._task_id = task_id
|
|
self._SandboxState = SandboxState
|
|
self._daytona = Daytona()
|
|
self._sandbox = None
|
|
self._lock = threading.Lock()
|
|
|
|
memory_gib = max(1, math.ceil(memory / 1024))
|
|
disk_gib = max(1, math.ceil(disk / 1024))
|
|
if disk_gib > 10:
|
|
logger.warning(
|
|
"Daytona: requested disk (%dGB) exceeds platform limit (10GB). "
|
|
"Capping to 10GB.", disk_gib,
|
|
)
|
|
disk_gib = 10
|
|
resources = Resources(cpu=cpu, memory=memory_gib, disk=disk_gib)
|
|
|
|
labels = {"hermes_task_id": task_id}
|
|
sandbox_name = f"hermes-{task_id}"
|
|
|
|
if self._persistent:
|
|
try:
|
|
self._sandbox = self._daytona.get(sandbox_name)
|
|
self._sandbox.start()
|
|
logger.info("Daytona: resumed sandbox %s for task %s",
|
|
self._sandbox.id, task_id)
|
|
except DaytonaError:
|
|
self._sandbox = None
|
|
except Exception as e:
|
|
logger.warning("Daytona: failed to resume sandbox for task %s: %s",
|
|
task_id, e)
|
|
self._sandbox = None
|
|
|
|
if self._sandbox is None:
|
|
try:
|
|
page = self._daytona.list(labels=labels, page=1, limit=1)
|
|
if page.items:
|
|
self._sandbox = page.items[0]
|
|
self._sandbox.start()
|
|
logger.info("Daytona: resumed legacy sandbox %s for task %s",
|
|
self._sandbox.id, task_id)
|
|
except Exception as e:
|
|
logger.debug("Daytona: no legacy sandbox found for task %s: %s",
|
|
task_id, e)
|
|
self._sandbox = None
|
|
|
|
if self._sandbox is None:
|
|
self._sandbox = self._daytona.create(
|
|
CreateSandboxFromImageParams(
|
|
image=image,
|
|
name=sandbox_name,
|
|
labels=labels,
|
|
auto_stop_interval=0,
|
|
resources=resources,
|
|
)
|
|
)
|
|
logger.info("Daytona: created sandbox %s for task %s",
|
|
self._sandbox.id, task_id)
|
|
|
|
# Detect remote home dir
|
|
self._remote_home = "/root"
|
|
try:
|
|
home = self._sandbox.process.exec("echo $HOME").result.strip()
|
|
if home:
|
|
self._remote_home = home
|
|
if requested_cwd in ("~", "/home/daytona"):
|
|
self.cwd = home
|
|
except Exception:
|
|
pass
|
|
logger.info("Daytona: resolved home to %s, cwd to %s", self._remote_home, self.cwd)
|
|
|
|
self._sync_manager = FileSyncManager(
|
|
get_files_fn=lambda: iter_sync_files(f"{self._remote_home}/.hermes"),
|
|
upload_fn=self._daytona_upload,
|
|
delete_fn=self._daytona_delete,
|
|
bulk_upload_fn=self._daytona_bulk_upload,
|
|
bulk_download_fn=self._daytona_bulk_download,
|
|
)
|
|
self._sync_manager.sync(force=True)
|
|
self.init_session()
|
|
|
|
def _daytona_upload(self, host_path: str, remote_path: str) -> None:
|
|
"""Upload a single file via Daytona SDK."""
|
|
parent = str(Path(remote_path).parent)
|
|
self._sandbox.process.exec(f"mkdir -p {parent}")
|
|
self._sandbox.fs.upload_file(host_path, remote_path)
|
|
|
|
def _daytona_bulk_upload(self, files: list[tuple[str, str]]) -> None:
|
|
"""Upload many files in a single HTTP call via Daytona SDK.
|
|
|
|
Uses ``sandbox.fs.upload_files()`` which batches all files into one
|
|
multipart POST, avoiding per-file TLS/HTTP overhead (~580 files
|
|
goes from ~5 min to <2 s).
|
|
"""
|
|
from daytona.common.filesystem import FileUpload
|
|
|
|
if not files:
|
|
return
|
|
|
|
parents = unique_parent_dirs(files)
|
|
if parents:
|
|
self._sandbox.process.exec(quoted_mkdir_command(parents))
|
|
|
|
uploads = [
|
|
FileUpload(source=host_path, destination=remote_path)
|
|
for host_path, remote_path in files
|
|
]
|
|
self._sandbox.fs.upload_files(uploads)
|
|
|
|
def _daytona_bulk_download(self, dest: Path) -> None:
|
|
"""Download remote .hermes/ as a tar archive."""
|
|
rel_base = f"{self._remote_home}/.hermes".lstrip("/")
|
|
self._sandbox.process.exec(
|
|
f"tar cf /tmp/.hermes_sync.tar -C / {shlex.quote(rel_base)}"
|
|
)
|
|
self._sandbox.fs.download_file("/tmp/.hermes_sync.tar", str(dest))
|
|
# Clean up remote temp file
|
|
try:
|
|
self._sandbox.process.exec("rm -f /tmp/.hermes_sync.tar")
|
|
except Exception:
|
|
pass # best-effort cleanup
|
|
|
|
def _daytona_delete(self, remote_paths: list[str]) -> None:
|
|
"""Batch-delete remote files via SDK exec."""
|
|
self._sandbox.process.exec(quoted_rm_command(remote_paths))
|
|
|
|
# ------------------------------------------------------------------
|
|
# Sandbox lifecycle
|
|
# ------------------------------------------------------------------
|
|
|
|
def _ensure_sandbox_ready(self) -> None:
|
|
"""Restart sandbox if it was stopped (e.g., by a previous interrupt)."""
|
|
self._sandbox.refresh_data()
|
|
if self._sandbox.state in (self._SandboxState.STOPPED, self._SandboxState.ARCHIVED):
|
|
self._sandbox.start()
|
|
logger.info("Daytona: restarted sandbox %s", self._sandbox.id)
|
|
|
|
def _before_execute(self) -> None:
|
|
"""Ensure sandbox is ready, then sync files via FileSyncManager."""
|
|
with self._lock:
|
|
self._ensure_sandbox_ready()
|
|
self._sync_manager.sync()
|
|
|
|
def _run_bash(self, cmd_string: str, *, login: bool = False,
|
|
timeout: int = 120,
|
|
stdin_data: str | None = None):
|
|
"""Return a _ThreadedProcessHandle wrapping a blocking Daytona SDK call."""
|
|
sandbox = self._sandbox
|
|
lock = self._lock
|
|
|
|
def cancel():
|
|
with lock:
|
|
try:
|
|
sandbox.stop()
|
|
except Exception:
|
|
pass
|
|
|
|
if login:
|
|
shell_cmd = f"bash -l -c {shlex.quote(cmd_string)}"
|
|
else:
|
|
shell_cmd = f"bash -c {shlex.quote(cmd_string)}"
|
|
|
|
def exec_fn() -> tuple[str, int]:
|
|
response = sandbox.process.exec(shell_cmd, timeout=timeout)
|
|
return (response.result or "", response.exit_code)
|
|
|
|
return _ThreadedProcessHandle(exec_fn, cancel_fn=cancel)
|
|
|
|
def cleanup(self):
|
|
if self._sync_manager:
|
|
logger.info("Daytona: syncing files from sandbox...")
|
|
self._sync_manager.sync_back()
|
|
|
|
with self._lock:
|
|
if self._sandbox is None:
|
|
return
|
|
try:
|
|
if self._persistent:
|
|
self._sandbox.stop()
|
|
logger.info("Daytona: stopped sandbox %s (filesystem preserved)",
|
|
self._sandbox.id)
|
|
else:
|
|
self._daytona.delete(self._sandbox)
|
|
logger.info("Daytona: deleted sandbox %s", self._sandbox.id)
|
|
except Exception as e:
|
|
logger.warning("Daytona: cleanup failed: %s", e)
|
|
self._sandbox = None
|