新增用户意图确认功能

This commit is contained in:
likun committed 2026-05-13 14:36:44 +08:00
1 parent cf2e4bdd9c
commit b8926f00d7
574 files changed
+97664 -97208

No files matched your search

@@ -1,15 +1,15 @@
from .aio_sandbox import AioSandbox
from .aio_sandbox_provider import AioSandboxProvider
from .backend import SandboxBackend
from .local_backend import LocalContainerBackend
from .remote_backend import RemoteSandboxBackend
from .sandbox_info import SandboxInfo
__all__ = [
"AioSandbox",
"AioSandboxProvider",
"LocalContainerBackend",
"RemoteSandboxBackend",
"SandboxBackend",
"SandboxInfo",
]
from .aio_sandbox import AioSandbox
from .aio_sandbox_provider import AioSandboxProvider
from .backend import SandboxBackend
from .local_backend import LocalContainerBackend
from .remote_backend import RemoteSandboxBackend
from .sandbox_info import SandboxInfo
__all__ = [
"AioSandbox",
"AioSandboxProvider",
"LocalContainerBackend",
"RemoteSandboxBackend",
"SandboxBackend",
"SandboxInfo",
]
@@ -1,238 +1,238 @@
import base64
import logging
import shlex
import threading
import uuid
from agent_sandbox import Sandbox as AioSandboxClient
from deerflow.sandbox.sandbox import Sandbox
from deerflow.sandbox.search import GrepMatch, path_matches, should_ignore_path, truncate_line
logger = logging.getLogger(__name__)
_ERROR_OBSERVATION_SIGNATURE = "'ErrorObservation' object has no attribute 'exit_code'"
class AioSandbox(Sandbox):
"""Sandbox implementation using the agent-infra/sandbox Docker container.
This sandbox connects to a running AIO sandbox container via HTTP API.
A threading lock serializes shell commands to prevent concurrent requests
from corrupting the container's single persistent session (see #1433).
"""
def __init__(self, id: str, base_url: str, home_dir: str | None = None):
"""Initialize the AIO sandbox.
Args:
id: Unique identifier for this sandbox instance.
base_url: URL of the sandbox API (e.g., http://localhost:8080).
home_dir: Home directory inside the sandbox. If None, will be fetched from the sandbox.
"""
super().__init__(id)
self._base_url = base_url
self._client = AioSandboxClient(base_url=base_url, timeout=600)
self._home_dir = home_dir
self._lock = threading.Lock()
@property
def base_url(self) -> str:
return self._base_url
@property
def home_dir(self) -> str:
"""Get the home directory inside the sandbox."""
if self._home_dir is None:
context = self._client.sandbox.get_context()
self._home_dir = context.home_dir
return self._home_dir
# Default no_change_timeout for exec_command (seconds). Matches the
# client-level timeout so that long-running commands which produce no
# output are not prematurely terminated by the sandbox's built-in 120 s
# default.
_DEFAULT_NO_CHANGE_TIMEOUT = 600
def execute_command(self, command: str) -> str:
"""Execute a shell command in the sandbox.
Uses a lock to serialize concurrent requests. The AIO sandbox
container maintains a single persistent shell session that
corrupts when hit with concurrent exec_command calls (returns
``ErrorObservation`` instead of real output). If corruption is
detected despite the lock (e.g. multiple processes sharing a
sandbox), the command is retried on a fresh session.
Args:
command: The command to execute.
Returns:
The output of the command.
"""
with self._lock:
try:
result = self._client.shell.exec_command(command=command, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
if output and _ERROR_OBSERVATION_SIGNATURE in output:
logger.warning("ErrorObservation detected in sandbox output, retrying with a fresh session")
fresh_id = str(uuid.uuid4())
result = self._client.shell.exec_command(command=command, id=fresh_id, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
return output if output else "(no output)"
except Exception as e:
logger.error(f"Failed to execute command in sandbox: {e}")
return f"Error: {e}"
def read_file(self, path: str) -> str:
"""Read the content of a file in the sandbox.
Args:
path: The absolute path of the file to read.
Returns:
The content of the file.
"""
try:
result = self._client.file.read_file(file=path)
return result.data.content if result.data else ""
except Exception as e:
logger.error(f"Failed to read file in sandbox: {e}")
return f"Error: {e}"
def list_dir(self, path: str, max_depth: int = 2) -> list[str]:
"""List the contents of a directory in the sandbox.
Args:
path: The absolute path of the directory to list.
max_depth: The maximum depth to traverse. Default is 2.
Returns:
The contents of the directory.
"""
with self._lock:
try:
result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500", no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
if output:
return [line.strip() for line in output.strip().split("\n") if line.strip()]
return []
except Exception as e:
logger.error(f"Failed to list directory in sandbox: {e}")
return []
def write_file(self, path: str, content: str, append: bool = False) -> None:
"""Write content to a file in the sandbox.
Args:
path: The absolute path of the file to write to.
content: The text content to write to the file.
append: Whether to append the content to the file.
"""
with self._lock:
try:
if append:
existing = self.read_file(path)
if not existing.startswith("Error:"):
content = existing + content
self._client.file.write_file(file=path, content=content)
except Exception as e:
logger.error(f"Failed to write file in sandbox: {e}")
raise
def glob(self, path: str, pattern: str, *, include_dirs: bool = False, max_results: int = 200) -> tuple[list[str], bool]:
if not include_dirs:
result = self._client.file.find_files(path=path, glob=pattern)
files = result.data.files if result.data and result.data.files else []
filtered = [file_path for file_path in files if not should_ignore_path(file_path)]
truncated = len(filtered) > max_results
return filtered[:max_results], truncated
result = self._client.file.list_path(path=path, recursive=True, show_hidden=False)
entries = result.data.files if result.data and result.data.files else []
matches: list[str] = []
root_path = path.rstrip("/") or "/"
root_prefix = root_path if root_path == "/" else f"{root_path}/"
for entry in entries:
if entry.path != root_path and not entry.path.startswith(root_prefix):
continue
if should_ignore_path(entry.path):
continue
rel_path = entry.path[len(root_path) :].lstrip("/")
if path_matches(pattern, rel_path):
matches.append(entry.path)
if len(matches) >= max_results:
return matches, True
return matches, False
def grep(
self,
path: str,
pattern: str,
*,
glob: str | None = None,
literal: bool = False,
case_sensitive: bool = False,
max_results: int = 100,
) -> tuple[list[GrepMatch], bool]:
import re as _re
regex_source = _re.escape(pattern) if literal else pattern
# Validate the pattern locally so an invalid regex raises re.error
# (caught by grep_tool's except re.error handler) rather than a
# generic remote API error.
_re.compile(regex_source, 0 if case_sensitive else _re.IGNORECASE)
regex = regex_source if case_sensitive else f"(?i){regex_source}"
if glob is not None:
find_result = self._client.file.find_files(path=path, glob=glob)
candidate_paths = find_result.data.files if find_result.data and find_result.data.files else []
else:
list_result = self._client.file.list_path(path=path, recursive=True, show_hidden=False)
entries = list_result.data.files if list_result.data and list_result.data.files else []
candidate_paths = [entry.path for entry in entries if not entry.is_directory]
matches: list[GrepMatch] = []
truncated = False
for file_path in candidate_paths:
if should_ignore_path(file_path):
continue
search_result = self._client.file.search_in_file(file=file_path, regex=regex)
data = search_result.data
if data is None:
continue
line_numbers = data.line_numbers or []
matched_lines = data.matches or []
for line_number, line in zip(line_numbers, matched_lines):
matches.append(
GrepMatch(
path=file_path,
line_number=line_number if isinstance(line_number, int) else 0,
line=truncate_line(line),
)
)
if len(matches) >= max_results:
truncated = True
return matches, truncated
return matches, truncated
def update_file(self, path: str, content: bytes) -> None:
"""Update a file with binary content in the sandbox.
Args:
path: The absolute path of the file to update.
content: The binary content to write to the file.
"""
with self._lock:
try:
base64_content = base64.b64encode(content).decode("utf-8")
self._client.file.write_file(file=path, content=base64_content, encoding="base64")
except Exception as e:
logger.error(f"Failed to update file in sandbox: {e}")
raise
import base64
import logging
import shlex
import threading
import uuid
from agent_sandbox import Sandbox as AioSandboxClient
from deerflow.sandbox.sandbox import Sandbox
from deerflow.sandbox.search import GrepMatch, path_matches, should_ignore_path, truncate_line
logger = logging.getLogger(__name__)
_ERROR_OBSERVATION_SIGNATURE = "'ErrorObservation' object has no attribute 'exit_code'"
class AioSandbox(Sandbox):
"""Sandbox implementation using the agent-infra/sandbox Docker container.
This sandbox connects to a running AIO sandbox container via HTTP API.
A threading lock serializes shell commands to prevent concurrent requests
from corrupting the container's single persistent session (see #1433).
"""
def __init__(self, id: str, base_url: str, home_dir: str | None = None):
"""Initialize the AIO sandbox.
Args:
id: Unique identifier for this sandbox instance.
base_url: URL of the sandbox API (e.g., http://localhost:8080).
home_dir: Home directory inside the sandbox. If None, will be fetched from the sandbox.
"""
super().__init__(id)
self._base_url = base_url
self._client = AioSandboxClient(base_url=base_url, timeout=600)
self._home_dir = home_dir
self._lock = threading.Lock()
@property
def base_url(self) -> str:
return self._base_url
@property
def home_dir(self) -> str:
"""Get the home directory inside the sandbox."""
if self._home_dir is None:
context = self._client.sandbox.get_context()
self._home_dir = context.home_dir
return self._home_dir
# Default no_change_timeout for exec_command (seconds). Matches the
# client-level timeout so that long-running commands which produce no
# output are not prematurely terminated by the sandbox's built-in 120 s
# default.
_DEFAULT_NO_CHANGE_TIMEOUT = 600
def execute_command(self, command: str) -> str:
"""Execute a shell command in the sandbox.
Uses a lock to serialize concurrent requests. The AIO sandbox
container maintains a single persistent shell session that
corrupts when hit with concurrent exec_command calls (returns
``ErrorObservation`` instead of real output). If corruption is
detected despite the lock (e.g. multiple processes sharing a
sandbox), the command is retried on a fresh session.
Args:
command: The command to execute.
Returns:
The output of the command.
"""
with self._lock:
try:
result = self._client.shell.exec_command(command=command, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
if output and _ERROR_OBSERVATION_SIGNATURE in output:
logger.warning("ErrorObservation detected in sandbox output, retrying with a fresh session")
fresh_id = str(uuid.uuid4())
result = self._client.shell.exec_command(command=command, id=fresh_id, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
return output if output else "(no output)"
except Exception as e:
logger.error(f"Failed to execute command in sandbox: {e}")
return f"Error: {e}"
def read_file(self, path: str) -> str:
"""Read the content of a file in the sandbox.
Args:
path: The absolute path of the file to read.
Returns:
The content of the file.
"""
try:
result = self._client.file.read_file(file=path)
return result.data.content if result.data else ""
except Exception as e:
logger.error(f"Failed to read file in sandbox: {e}")
return f"Error: {e}"
def list_dir(self, path: str, max_depth: int = 2) -> list[str]:
"""List the contents of a directory in the sandbox.
Args:
path: The absolute path of the directory to list.
max_depth: The maximum depth to traverse. Default is 2.
Returns:
The contents of the directory.
"""
with self._lock:
try:
result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500", no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
output = result.data.output if result.data else ""
if output:
return [line.strip() for line in output.strip().split("\n") if line.strip()]
return []
except Exception as e:
logger.error(f"Failed to list directory in sandbox: {e}")
return []
def write_file(self, path: str, content: str, append: bool = False) -> None:
"""Write content to a file in the sandbox.
Args:
path: The absolute path of the file to write to.
content: The text content to write to the file.
append: Whether to append the content to the file.
"""
with self._lock:
try:
if append:
existing = self.read_file(path)
if not existing.startswith("Error:"):
content = existing + content
self._client.file.write_file(file=path, content=content)
except Exception as e:
logger.error(f"Failed to write file in sandbox: {e}")
raise
def glob(self, path: str, pattern: str, *, include_dirs: bool = False, max_results: int = 200) -> tuple[list[str], bool]:
if not include_dirs:
result = self._client.file.find_files(path=path, glob=pattern)
files = result.data.files if result.data and result.data.files else []
filtered = [file_path for file_path in files if not should_ignore_path(file_path)]
truncated = len(filtered) > max_results
return filtered[:max_results], truncated
result = self._client.file.list_path(path=path, recursive=True, show_hidden=False)
entries = result.data.files if result.data and result.data.files else []
matches: list[str] = []
root_path = path.rstrip("/") or "/"
root_prefix = root_path if root_path == "/" else f"{root_path}/"
for entry in entries:
if entry.path != root_path and not entry.path.startswith(root_prefix):
continue
if should_ignore_path(entry.path):
continue
rel_path = entry.path[len(root_path) :].lstrip("/")
if path_matches(pattern, rel_path):
matches.append(entry.path)
if len(matches) >= max_results:
return matches, True
return matches, False
def grep(
self,
path: str,
pattern: str,
*,
glob: str | None = None,
literal: bool = False,
case_sensitive: bool = False,
max_results: int = 100,
) -> tuple[list[GrepMatch], bool]:
import re as _re
regex_source = _re.escape(pattern) if literal else pattern
# Validate the pattern locally so an invalid regex raises re.error
# (caught by grep_tool's except re.error handler) rather than a
# generic remote API error.
_re.compile(regex_source, 0 if case_sensitive else _re.IGNORECASE)
regex = regex_source if case_sensitive else f"(?i){regex_source}"
if glob is not None:
find_result = self._client.file.find_files(path=path, glob=glob)
candidate_paths = find_result.data.files if find_result.data and find_result.data.files else []
else:
list_result = self._client.file.list_path(path=path, recursive=True, show_hidden=False)
entries = list_result.data.files if list_result.data and list_result.data.files else []
candidate_paths = [entry.path for entry in entries if not entry.is_directory]
matches: list[GrepMatch] = []
truncated = False
for file_path in candidate_paths:
if should_ignore_path(file_path):
continue
search_result = self._client.file.search_in_file(file=file_path, regex=regex)
data = search_result.data
if data is None:
continue
line_numbers = data.line_numbers or []
matched_lines = data.matches or []
for line_number, line in zip(line_numbers, matched_lines):
matches.append(
GrepMatch(
path=file_path,
line_number=line_number if isinstance(line_number, int) else 0,
line=truncate_line(line),
)
)
if len(matches) >= max_results:
truncated = True
return matches, truncated
return matches, truncated
def update_file(self, path: str, content: bytes) -> None:
"""Update a file with binary content in the sandbox.
Args:
path: The absolute path of the file to update.
content: The binary content to write to the file.
"""
with self._lock:
try:
base64_content = base64.b64encode(content).decode("utf-8")
self._client.file.write_file(file=path, content=base64_content, encoding="base64")
except Exception as e:
logger.error(f"Failed to update file in sandbox: {e}")
raise
@@ -1,114 +1,114 @@
"""Abstract base class for sandbox provisioning backends."""
from __future__ import annotations
import logging
import time
from abc import ABC, abstractmethod
import requests
from .sandbox_info import SandboxInfo
logger = logging.getLogger(__name__)
def wait_for_sandbox_ready(sandbox_url: str, timeout: int = 30) -> bool:
"""Poll sandbox health endpoint until ready or timeout.
Args:
sandbox_url: URL of the sandbox (e.g. http://k3s:30001).
timeout: Maximum time to wait in seconds.
Returns:
True if sandbox is ready, False otherwise.
"""
start_time = time.time()
while time.time() - start_time < timeout:
try:
response = requests.get(f"{sandbox_url}/v1/sandbox", timeout=5)
if response.status_code == 200:
return True
except requests.exceptions.RequestException:
pass
time.sleep(1)
return False
class SandboxBackend(ABC):
"""Abstract base for sandbox provisioning backends.
Two implementations:
- LocalContainerBackend: starts Docker/Apple Container locally, manages ports
- RemoteSandboxBackend: connects to a pre-existing URL (K8s service, external)
"""
@abstractmethod
def create(self, thread_id: str, sandbox_id: str, extra_mounts: list[tuple[str, str, bool]] | None = None) -> SandboxInfo:
"""Create/provision a new sandbox.
Args:
thread_id: Thread ID for which the sandbox is being created. Useful for backends that want to organize sandboxes by thread.
sandbox_id: Deterministic sandbox identifier.
extra_mounts: Additional volume mounts as (host_path, container_path, read_only) tuples.
Ignored by backends that don't manage containers (e.g., remote).
Returns:
SandboxInfo with connection details.
"""
...
@abstractmethod
def destroy(self, info: SandboxInfo) -> None:
"""Destroy/cleanup a sandbox and release its resources.
Args:
info: The sandbox metadata to destroy.
"""
...
@abstractmethod
def is_alive(self, info: SandboxInfo) -> bool:
"""Quick check whether a sandbox is still alive.
This should be a lightweight check (e.g., container inspect)
rather than a full health check.
Args:
info: The sandbox metadata to check.
Returns:
True if the sandbox appears to be alive.
"""
...
@abstractmethod
def discover(self, sandbox_id: str) -> SandboxInfo | None:
"""Try to discover an existing sandbox by its deterministic ID.
Used for cross-process recovery: when another process started a sandbox,
this process can discover it by the deterministic container name or URL.
Args:
sandbox_id: The deterministic sandbox ID to look for.
Returns:
SandboxInfo if found and healthy, None otherwise.
"""
...
def list_running(self) -> list[SandboxInfo]:
"""Enumerate all running sandboxes managed by this backend.
Used for startup reconciliation: when the process restarts, it needs
to discover containers started by previous processes so they can be
adopted into the warm pool or destroyed if idle too long.
The default implementation returns an empty list, which is correct
for backends that don't manage local containers (e.g., RemoteSandboxBackend
delegates lifecycle to the provisioner which handles its own cleanup).
Returns:
A list of SandboxInfo for all currently running sandboxes.
"""
return []
"""Abstract base class for sandbox provisioning backends."""
from __future__ import annotations
import logging
import time
from abc import ABC, abstractmethod
import requests
from .sandbox_info import SandboxInfo
logger = logging.getLogger(__name__)
def wait_for_sandbox_ready(sandbox_url: str, timeout: int = 30) -> bool:
"""Poll sandbox health endpoint until ready or timeout.
Args:
sandbox_url: URL of the sandbox (e.g. http://k3s:30001).
timeout: Maximum time to wait in seconds.
Returns:
True if sandbox is ready, False otherwise.
"""
start_time = time.time()
while time.time() - start_time < timeout:
try:
response = requests.get(f"{sandbox_url}/v1/sandbox", timeout=5)
if response.status_code == 200:
return True
except requests.exceptions.RequestException:
pass
time.sleep(1)
return False
class SandboxBackend(ABC):
"""Abstract base for sandbox provisioning backends.
Two implementations:
- LocalContainerBackend: starts Docker/Apple Container locally, manages ports
- RemoteSandboxBackend: connects to a pre-existing URL (K8s service, external)
"""
@abstractmethod
def create(self, thread_id: str, sandbox_id: str, extra_mounts: list[tuple[str, str, bool]] | None = None) -> SandboxInfo:
"""Create/provision a new sandbox.
Args:
thread_id: Thread ID for which the sandbox is being created. Useful for backends that want to organize sandboxes by thread.
sandbox_id: Deterministic sandbox identifier.
extra_mounts: Additional volume mounts as (host_path, container_path, read_only) tuples.
Ignored by backends that don't manage containers (e.g., remote).
Returns:
SandboxInfo with connection details.
"""
...
@abstractmethod
def destroy(self, info: SandboxInfo) -> None:
"""Destroy/cleanup a sandbox and release its resources.
Args:
info: The sandbox metadata to destroy.
"""
...
@abstractmethod
def is_alive(self, info: SandboxInfo) -> bool:
"""Quick check whether a sandbox is still alive.
This should be a lightweight check (e.g., container inspect)
rather than a full health check.
Args:
info: The sandbox metadata to check.
Returns:
True if the sandbox appears to be alive.
"""
...
@abstractmethod
def discover(self, sandbox_id: str) -> SandboxInfo | None:
"""Try to discover an existing sandbox by its deterministic ID.
Used for cross-process recovery: when another process started a sandbox,
this process can discover it by the deterministic container name or URL.
Args:
sandbox_id: The deterministic sandbox ID to look for.
Returns:
SandboxInfo if found and healthy, None otherwise.
"""
...
def list_running(self) -> list[SandboxInfo]:
"""Enumerate all running sandboxes managed by this backend.
Used for startup reconciliation: when the process restarts, it needs
to discover containers started by previous processes so they can be
adopted into the warm pool or destroyed if idle too long.
The default implementation returns an empty list, which is correct
for backends that don't manage local containers (e.g., RemoteSandboxBackend
delegates lifecycle to the provisioner which handles its own cleanup).
Returns:
A list of SandboxInfo for all currently running sandboxes.
"""
return []
@@ -1,156 +1,156 @@
"""Remote sandbox backend — delegates Pod lifecycle to the provisioner service.
The provisioner dynamically creates per-sandbox-id Pods + NodePort Services
in k3s. The backend accesses sandbox pods directly via ``k3s:{NodePort}``.
Architecture:
┌────────────┐ HTTP ┌─────────────┐ K8s API ┌──────────┐
│ this file │ ──────▸ │ provisioner │ ────────▸ │ k3s │
│ (backend) │ │ :8002 │ │ :6443 │
└────────────┘ └─────────────┘ └─────┬────┘
│ creates
┌─────────────┐ ┌─────▼──────┐
│ backend │ ────────▸ │ sandbox │
│ │ direct │ Pod(s) │
└─────────────┘ k3s:NPort └────────────┘
"""
from __future__ import annotations
import logging
import requests
from .backend import SandboxBackend
from .sandbox_info import SandboxInfo
logger = logging.getLogger(__name__)
class RemoteSandboxBackend(SandboxBackend):
"""Backend that delegates sandbox lifecycle to the provisioner service.
All Pod creation, destruction, and discovery are handled by the
provisioner. This backend is a thin HTTP client.
Typical config.yaml::
sandbox:
use: deerflow.community.aio_sandbox:AioSandboxProvider
provisioner_url: http://provisioner:8002
"""
def __init__(self, provisioner_url: str):
"""Initialize with the provisioner service URL.
Args:
provisioner_url: URL of the provisioner service
(e.g., ``http://provisioner:8002``).
"""
self._provisioner_url = provisioner_url.rstrip("/")
@property
def provisioner_url(self) -> str:
return self._provisioner_url
# ── SandboxBackend interface ──────────────────────────────────────────
def create(
self,
thread_id: str,
sandbox_id: str,
extra_mounts: list[tuple[str, str, bool]] | None = None,
) -> SandboxInfo:
"""Create a sandbox Pod + Service via the provisioner.
Calls ``POST /api/sandboxes`` which creates a dedicated Pod +
NodePort Service in k3s.
"""
return self._provisioner_create(thread_id, sandbox_id, extra_mounts)
def destroy(self, info: SandboxInfo) -> None:
"""Destroy a sandbox Pod + Service via the provisioner."""
self._provisioner_destroy(info.sandbox_id)
def is_alive(self, info: SandboxInfo) -> bool:
"""Check whether the sandbox Pod is running."""
return self._provisioner_is_alive(info.sandbox_id)
def discover(self, sandbox_id: str) -> SandboxInfo | None:
"""Discover an existing sandbox via the provisioner.
Calls ``GET /api/sandboxes/{sandbox_id}`` and returns info if
the Pod exists.
"""
return self._provisioner_discover(sandbox_id)
# ── Provisioner API calls ─────────────────────────────────────────────
def _provisioner_create(self, thread_id: str, sandbox_id: str, extra_mounts: list[tuple[str, str, bool]] | None = None) -> SandboxInfo:
"""POST /api/sandboxes → create Pod + Service."""
try:
resp = requests.post(
f"{self._provisioner_url}/api/sandboxes",
json={
"sandbox_id": sandbox_id,
"thread_id": thread_id,
},
timeout=30,
)
resp.raise_for_status()
data = resp.json()
logger.info(f"Provisioner created sandbox {sandbox_id}: sandbox_url={data['sandbox_url']}")
return SandboxInfo(
sandbox_id=sandbox_id,
sandbox_url=data["sandbox_url"],
)
except requests.RequestException as exc:
logger.error(f"Provisioner create failed for {sandbox_id}: {exc}")
raise RuntimeError(f"Provisioner create failed: {exc}") from exc
def _provisioner_destroy(self, sandbox_id: str) -> None:
"""DELETE /api/sandboxes/{sandbox_id} → destroy Pod + Service."""
try:
resp = requests.delete(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=15,
)
if resp.ok:
logger.info(f"Provisioner destroyed sandbox {sandbox_id}")
else:
logger.warning(f"Provisioner destroy returned {resp.status_code}: {resp.text}")
except requests.RequestException as exc:
logger.warning(f"Provisioner destroy failed for {sandbox_id}: {exc}")
def _provisioner_is_alive(self, sandbox_id: str) -> bool:
"""GET /api/sandboxes/{sandbox_id} → check Pod phase."""
try:
resp = requests.get(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=10,
)
if resp.ok:
data = resp.json()
return data.get("status") == "Running"
return False
except requests.RequestException:
return False
def _provisioner_discover(self, sandbox_id: str) -> SandboxInfo | None:
"""GET /api/sandboxes/{sandbox_id} → discover existing sandbox."""
try:
resp = requests.get(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=10,
)
if resp.status_code == 404:
return None
resp.raise_for_status()
data = resp.json()
return SandboxInfo(
sandbox_id=sandbox_id,
sandbox_url=data["sandbox_url"],
)
except requests.RequestException as exc:
logger.debug(f"Provisioner discover failed for {sandbox_id}: {exc}")
return None
"""Remote sandbox backend — delegates Pod lifecycle to the provisioner service.
The provisioner dynamically creates per-sandbox-id Pods + NodePort Services
in k3s. The backend accesses sandbox pods directly via ``k3s:{NodePort}``.
Architecture:
┌────────────┐ HTTP ┌─────────────┐ K8s API ┌──────────┐
│ this file │ ──────▸ │ provisioner │ ────────▸ │ k3s │
│ (backend) │ │ :8002 │ │ :6443 │
└────────────┘ └─────────────┘ └─────┬────┘
│ creates
┌─────────────┐ ┌─────▼──────┐
│ backend │ ────────▸ │ sandbox │
│ │ direct │ Pod(s) │
└─────────────┘ k3s:NPort └────────────┘
"""
from __future__ import annotations
import logging
import requests
from .backend import SandboxBackend
from .sandbox_info import SandboxInfo
logger = logging.getLogger(__name__)
class RemoteSandboxBackend(SandboxBackend):
"""Backend that delegates sandbox lifecycle to the provisioner service.
All Pod creation, destruction, and discovery are handled by the
provisioner. This backend is a thin HTTP client.
Typical config.yaml::
sandbox:
use: deerflow.community.aio_sandbox:AioSandboxProvider
provisioner_url: http://provisioner:8002
"""
def __init__(self, provisioner_url: str):
"""Initialize with the provisioner service URL.
Args:
provisioner_url: URL of the provisioner service
(e.g., ``http://provisioner:8002``).
"""
self._provisioner_url = provisioner_url.rstrip("/")
@property
def provisioner_url(self) -> str:
return self._provisioner_url
# ── SandboxBackend interface ──────────────────────────────────────────
def create(
self,
thread_id: str,
sandbox_id: str,
extra_mounts: list[tuple[str, str, bool]] | None = None,
) -> SandboxInfo:
"""Create a sandbox Pod + Service via the provisioner.
Calls ``POST /api/sandboxes`` which creates a dedicated Pod +
NodePort Service in k3s.
"""
return self._provisioner_create(thread_id, sandbox_id, extra_mounts)
def destroy(self, info: SandboxInfo) -> None:
"""Destroy a sandbox Pod + Service via the provisioner."""
self._provisioner_destroy(info.sandbox_id)
def is_alive(self, info: SandboxInfo) -> bool:
"""Check whether the sandbox Pod is running."""
return self._provisioner_is_alive(info.sandbox_id)
def discover(self, sandbox_id: str) -> SandboxInfo | None:
"""Discover an existing sandbox via the provisioner.
Calls ``GET /api/sandboxes/{sandbox_id}`` and returns info if
the Pod exists.
"""
return self._provisioner_discover(sandbox_id)
# ── Provisioner API calls ─────────────────────────────────────────────
def _provisioner_create(self, thread_id: str, sandbox_id: str, extra_mounts: list[tuple[str, str, bool]] | None = None) -> SandboxInfo:
"""POST /api/sandboxes → create Pod + Service."""
try:
resp = requests.post(
f"{self._provisioner_url}/api/sandboxes",
json={
"sandbox_id": sandbox_id,
"thread_id": thread_id,
},
timeout=30,
)
resp.raise_for_status()
data = resp.json()
logger.info(f"Provisioner created sandbox {sandbox_id}: sandbox_url={data['sandbox_url']}")
return SandboxInfo(
sandbox_id=sandbox_id,
sandbox_url=data["sandbox_url"],
)
except requests.RequestException as exc:
logger.error(f"Provisioner create failed for {sandbox_id}: {exc}")
raise RuntimeError(f"Provisioner create failed: {exc}") from exc
def _provisioner_destroy(self, sandbox_id: str) -> None:
"""DELETE /api/sandboxes/{sandbox_id} → destroy Pod + Service."""
try:
resp = requests.delete(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=15,
)
if resp.ok:
logger.info(f"Provisioner destroyed sandbox {sandbox_id}")
else:
logger.warning(f"Provisioner destroy returned {resp.status_code}: {resp.text}")
except requests.RequestException as exc:
logger.warning(f"Provisioner destroy failed for {sandbox_id}: {exc}")
def _provisioner_is_alive(self, sandbox_id: str) -> bool:
"""GET /api/sandboxes/{sandbox_id} → check Pod phase."""
try:
resp = requests.get(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=10,
)
if resp.ok:
data = resp.json()
return data.get("status") == "Running"
return False
except requests.RequestException:
return False
def _provisioner_discover(self, sandbox_id: str) -> SandboxInfo | None:
"""GET /api/sandboxes/{sandbox_id} → discover existing sandbox."""
try:
resp = requests.get(
f"{self._provisioner_url}/api/sandboxes/{sandbox_id}",
timeout=10,
)
if resp.status_code == 404:
return None
resp.raise_for_status()
data = resp.json()
return SandboxInfo(
sandbox_id=sandbox_id,
sandbox_url=data["sandbox_url"],
)
except requests.RequestException as exc:
logger.debug(f"Provisioner discover failed for {sandbox_id}: {exc}")
return None
@@ -1,41 +1,41 @@
"""Sandbox metadata for cross-process discovery and state persistence."""
from __future__ import annotations
import time
from dataclasses import dataclass, field
@dataclass
class SandboxInfo:
"""Persisted sandbox metadata that enables cross-process discovery.
This dataclass holds all the information needed to reconnect to an
existing sandbox from a different process (e.g., gateway vs langgraph,
multiple workers, or across K8s pods with shared storage).
"""
sandbox_id: str
sandbox_url: str # e.g. http://localhost:8080 or http://k3s:30001
container_name: str | None = None # Only for local container backend
container_id: str | None = None # Only for local container backend
created_at: float = field(default_factory=time.time)
def to_dict(self) -> dict:
return {
"sandbox_id": self.sandbox_id,
"sandbox_url": self.sandbox_url,
"container_name": self.container_name,
"container_id": self.container_id,
"created_at": self.created_at,
}
@classmethod
def from_dict(cls, data: dict) -> SandboxInfo:
return cls(
sandbox_id=data["sandbox_id"],
sandbox_url=data.get("sandbox_url", data.get("base_url", "")),
container_name=data.get("container_name"),
container_id=data.get("container_id"),
created_at=data.get("created_at", time.time()),
)
"""Sandbox metadata for cross-process discovery and state persistence."""
from __future__ import annotations
import time
from dataclasses import dataclass, field
@dataclass
class SandboxInfo:
"""Persisted sandbox metadata that enables cross-process discovery.
This dataclass holds all the information needed to reconnect to an
existing sandbox from a different process (e.g., gateway vs langgraph,
multiple workers, or across K8s pods with shared storage).
"""
sandbox_id: str
sandbox_url: str # e.g. http://localhost:8080 or http://k3s:30001
container_name: str | None = None # Only for local container backend
container_id: str | None = None # Only for local container backend
created_at: float = field(default_factory=time.time)
def to_dict(self) -> dict:
return {
"sandbox_id": self.sandbox_id,
"sandbox_url": self.sandbox_url,
"container_name": self.container_name,
"container_id": self.container_id,
"created_at": self.created_at,
}
@classmethod
def from_dict(cls, data: dict) -> SandboxInfo:
return cls(
sandbox_id=data["sandbox_id"],
sandbox_url=data.get("sandbox_url", data.get("base_url", "")),
container_name=data.get("container_name"),
container_id=data.get("container_id"),
created_at=data.get("created_at", time.time()),
)