furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-06-10 17:35:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(tool-output-budget): only consult sandbox provider when a sandbox is resolved

Browse Source 
The previous revision called get_sandbox_provider() whenever externalization
was triggered, including on the legacy host-disk path. Environments without
a configured sandbox -- in particular CI runners without a config.yaml --
would raise FileNotFoundError there, get caught, and silently fall back to
inline truncation. That defeated the host-disk externalization path that
predates this PR and was the root cause of the regressing legacy tests.

Restructure the branching so the provider is only consulted when a sandbox
has actually been resolved for the current tool call:

  - sandbox resolved + provider.uses_thread_data_mounts: host-disk write
    (bind-mounted into the sandbox, equivalent to a sandbox-side write).
  - sandbox resolved + non-mounted provider:             sandbox write (#3416).
  - no sandbox + outputs_path:                           host-disk write
    (legacy / non-sandbox tools, no provider call at all).
  - otherwise:                                           inline fallback.

No test changes; the legacy externalization tests are provider-agnostic by
construction and now pass without monkeypatching.

Refs: #3416
This commit is contained in:
Huixin615
2026-06-08 09:32:29 +08:00
parent c837768242
commit d6e2d25b32
1 changed files with 28 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/packages/harness/deerflow/agents/middlewares/tool_output_budget_middleware.py
+28 -13
View File
@@ -340,32 +340,47 @@ def _budget_content(
if threshold > 0 and len(content) > threshold:
virtual_path: str | None = None
provider = None
if outputs_path or sandbox is not None:
# Decide persistence target based on what's available, without touching
# the sandbox provider unless a sandbox was actually resolved for this
# call. This keeps the legacy host-disk path provider-free, so callers
# without a configured sandbox (and CI environments without a
# config.yaml) continue to externalize to the host as before.
if sandbox is not None:
provider = None
try:
provider = get_sandbox_provider()
except Exception:
logger.exception("Failed to get sandbox provider for tool-output externalization; falling back to inline truncation")
if provider is not None and getattr(provider, "uses_thread_data_mounts", False):
# Host-mounted sandbox: the host outputs path is bind-mounted into
# the sandbox at the same virtual path, so writing host-side is
# equivalent to writing sandbox-side. Preserve the original
# behavior to avoid extra sandbox round-trips.
if outputs_path:
virtual_path = _externalize(
if provider is not None and getattr(provider, "uses_thread_data_mounts", False):
# Host-mounted sandbox: host outputs path is bind-mounted into
# the sandbox at the same virtual path, so writing host-side is
# equivalent. Preserve the original behavior to avoid extra
# sandbox round-trips.
if outputs_path:
virtual_path = _externalize(
content,
tool_name=tool_name,
tool_call_id=tool_call_id,
outputs_path=outputs_path,
storage_subdir=config.storage_subdir,
)
else:
virtual_path = _externalize_to_sandbox(
content,
tool_name=tool_name,
tool_call_id=tool_call_id,
outputs_path=outputs_path,
storage_subdir=config.storage_subdir,
sandbox=sandbox,
)
elif sandbox is not None:
virtual_path = _externalize_to_sandbox(
elif outputs_path:
# No sandbox in this call (legacy / non-sandbox tools): write to
# host outputs path directly, no provider needed.
virtual_path = _externalize(
content,
tool_name=tool_name,
tool_call_id=tool_call_id,
outputs_path=outputs_path,
storage_subdir=config.storage_subdir,
sandbox=sandbox,
)
if virtual_path is not None:
logger.info(