mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-25 11:18:22 +00:00
df5339b5d0
* feat(sandbox): truncate oversized bash and read_file tool outputs Long tool outputs (large directory listings, multi-MB source files) can overflow the model's context window. Two new configurable limits: - bash_output_max_chars (default 20000): middle-truncates bash output, preserving both head and tail so stderr at the end is not lost - read_file_output_max_chars (default 50000): head-truncates file output with a hint to use start_line/end_line for targeted reads Both limits are enforced at the tool layer (sandbox/tools.py) rather than middleware, so truncation is guaranteed regardless of call path. Setting either limit to 0 disables truncation entirely. Measured: read_file on a 250KB source file drops from 63,698 tokens to 19,927 tokens (69% reduction) with the default limit. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(tests): remove unused pytest import and fix import sort order * style: apply ruff format to sandbox/tools.py * refactor(sandbox): address Copilot review feedback on truncation feature - strict hard cap: while-loop ensures result (including marker) ≤ max_chars - max_chars=0 now returns "" instead of original output - get_app_config() wrapped in try/except with fallback to defaults - sandbox_config.py: add ge=0 validation on truncation limit fields - config.example.yaml: bump config_version 4→5 - tests: add len(result) <= max_chars assertions, edge-case (max=0, small max, various sizes) tests; fix skipped-count test for strict hard cap * refactor(sandbox): replace while-loop truncation with fixed marker budget Use a pre-allocated constant (_MARKER_MAX_LEN) instead of a convergence loop to ensure result <= max_chars. Simpler, safer, and skipped-char count in the marker is now an exact predictable value. * refactor(sandbox): compute marker budget dynamically instead of hardcoding * fix(sandbox): make max_chars=0 disable truncation instead of returning empty string --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> Co-authored-by: JeffJiang <for-eleven@hotmail.com>
79 lines
3.6 KiB
Python
79 lines
3.6 KiB
Python
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
|
|
class VolumeMountConfig(BaseModel):
|
|
"""Configuration for a volume mount."""
|
|
|
|
host_path: str = Field(..., description="Path on the host machine")
|
|
container_path: str = Field(..., description="Path inside the container")
|
|
read_only: bool = Field(default=False, description="Whether the mount is read-only")
|
|
|
|
|
|
class SandboxConfig(BaseModel):
|
|
"""Config section for a sandbox.
|
|
|
|
Common options:
|
|
use: Class path of the sandbox provider (required)
|
|
allow_host_bash: Enable host-side bash execution for LocalSandboxProvider.
|
|
Dangerous and intended only for fully trusted local workflows.
|
|
|
|
AioSandboxProvider specific options:
|
|
image: Docker image to use (default: enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest)
|
|
port: Base port for sandbox containers (default: 8080)
|
|
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.
|
|
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)
|
|
"""
|
|
|
|
use: str = Field(
|
|
...,
|
|
description="Class path of the sandbox provider (e.g. deerflow.sandbox.local:LocalSandboxProvider)",
|
|
)
|
|
allow_host_bash: bool = Field(
|
|
default=False,
|
|
description="Allow the bash tool to execute directly on the host when using LocalSandboxProvider. Dangerous; intended only for fully trusted local environments.",
|
|
)
|
|
image: str | None = Field(
|
|
default=None,
|
|
description="Docker image to use for the sandbox container",
|
|
)
|
|
port: int | None = Field(
|
|
default=None,
|
|
description="Base port for sandbox containers",
|
|
)
|
|
replicas: int | None = Field(
|
|
default=None,
|
|
description="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: str | None = Field(
|
|
default=None,
|
|
description="Prefix for container names",
|
|
)
|
|
idle_timeout: int | None = Field(
|
|
default=None,
|
|
description="Idle timeout in seconds before sandbox is released (default: 600 = 10 minutes). Set to 0 to disable.",
|
|
)
|
|
mounts: list[VolumeMountConfig] = Field(
|
|
default_factory=list,
|
|
description="List of volume mounts to share directories between host and container",
|
|
)
|
|
environment: dict[str, str] = Field(
|
|
default_factory=dict,
|
|
description="Environment variables to inject into the sandbox container. Values starting with $ will be resolved from host environment variables.",
|
|
)
|
|
|
|
bash_output_max_chars: int = Field(
|
|
default=20000,
|
|
ge=0,
|
|
description="Maximum characters to keep from bash tool output. Output exceeding this limit is middle-truncated (head + tail), preserving the first and last half. Set to 0 to disable truncation.",
|
|
)
|
|
read_file_output_max_chars: int = Field(
|
|
default=50000,
|
|
ge=0,
|
|
description="Maximum characters to keep from read_file tool output. Output exceeding this limit is head-truncated. Set to 0 to disable truncation.",
|
|
)
|
|
|
|
model_config = ConfigDict(extra="allow")
|