furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-05-24 17:06:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(sandbox): auto-restart crashed containers transparently (#2788)

Browse Source 
When a sandbox container crashes (e.g. due to an internal error), the
  agent enters a connection-refused loop because AioSandboxProvider.get()
  returns a cached but dead sandbox object. Add a liveness check in get()
  that detects crashed containers via backend.is_alive() and evicts them
  from all caches, allowing ensure_sandbox_initialized() to transparently
  recreate a fresh container on the next acquire().

  The behavior is controlled by a new  config option
  (default: true). Set to false to skip health checks and preserve the
  old behavior of returning stale cached sandboxes.

  Closes #2788
This commit is contained in:
Willem Jiang
2026-05-10 22:53:58 +08:00
parent 94da8f67d7
commit b67c2a4e56
4 changed files with 217 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/packages/harness/deerflow/config/sandbox_config.py
+7
View File
@@ -23,6 +23,9 @@ class SandboxConfig(BaseModel):
replicas: Maximum number of concurrent sandbox containers (default: 3). When the limit is reached the least-recently-used sandbox is evicted to make room.
container_prefix: Prefix for container names (default: deer-flow-sandbox)
idle_timeout: Idle timeout in seconds before sandbox is released (default: 600 = 10 minutes). Set to 0 to disable.
auto_restart: Automatically restart sandbox containers that have crashed (default: true). When a tool call
detects the container is no longer alive, the sandbox is evicted from cache and transparently recreated
on the next acquire. Set to false to disable.
mounts: List of volume mounts to share directories with the container
environment: Environment variables to inject into the container (values starting with $ are resolved from host env)
"""
@@ -55,6 +58,10 @@ class SandboxConfig(BaseModel):
default=None,
description="Idle timeout in seconds before sandbox is released (default: 600 = 10 minutes). Set to 0 to disable.",
)
auto_restart: bool = Field(
default=True,
description="Automatically restart sandbox containers that have crashed. When a tool call detects the container is no longer alive, the sandbox is evicted from cache and transparently recreated on the next acquire.",
)
mounts: list[VolumeMountConfig] = Field(
default_factory=list,
description="List of volume mounts to share directories between host and container",