mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-16 09:22:22 +00:00
fix(code_interpreter): delete only the session sandbox that failed, never its replacement
This commit is contained in:
parent
ef28e097bb
commit
c056772ea3
2 changed files with 83 additions and 31 deletions
|
|
@ -529,7 +529,7 @@ class CodeInterpreterInterceptionLogger(CustomLogger):
|
|||
except Exception:
|
||||
await self._delete_container_for_cache_key(sandbox_key)
|
||||
raise
|
||||
await self._evict_sandbox_if_a_run_failed(sandbox_key, code_interpreter_calls)
|
||||
await self._evict_sandbox_if_a_run_failed(sandbox_key, sandbox, code_interpreter_calls)
|
||||
|
||||
optional_params: Final = anthropic_messages_optional_request_params
|
||||
request_patch: Final = AgenticLoopRequestPatch(
|
||||
|
|
@ -584,7 +584,7 @@ class CodeInterpreterInterceptionLogger(CustomLogger):
|
|||
raise
|
||||
tool_messages: Final = [result[0] for result in tool_results]
|
||||
code_interpreter_calls: Final = [result[1] for result in tool_results]
|
||||
await self._evict_sandbox_if_a_run_failed(sandbox_key, code_interpreter_calls)
|
||||
await self._evict_sandbox_if_a_run_failed(sandbox_key, sandbox, code_interpreter_calls)
|
||||
|
||||
request_patch: Final = AgenticLoopRequestPatch(
|
||||
model=model,
|
||||
|
|
@ -739,10 +739,17 @@ class CodeInterpreterInterceptionLogger(CustomLogger):
|
|||
return ""
|
||||
|
||||
async def _evict_sandbox_if_a_run_failed(
|
||||
self, sandbox_key: str | None, calls: Sequence[CodeInterpreterCall]
|
||||
self, sandbox_key: str | None, sandbox: _Sandbox, calls: Sequence[CodeInterpreterCall]
|
||||
) -> None:
|
||||
if any(call["status"] == "failed" for call in calls):
|
||||
await self._delete_container_for_cache_key(sandbox_key)
|
||||
if not sandbox_key or not isinstance(sandbox, _ReadySandbox):
|
||||
return
|
||||
if not any(call["status"] == "failed" for call in calls):
|
||||
return
|
||||
cached: Final = self._container_cache.get(sandbox_key)
|
||||
if cached is None or cached[0] is not sandbox.container:
|
||||
return
|
||||
self._container_cache.pop(sandbox_key)
|
||||
await self._delete_container(container=cached[0], params=cached[1])
|
||||
|
||||
async def _sandbox_tool_output(self, sandbox: _Sandbox, arguments: str) -> _ToolRun:
|
||||
match sandbox:
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@ All sandbox dependencies are injected: a FakeSandbox stands in for the real e2b
|
|||
config and records how it is called.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import time
|
||||
from typing import Final
|
||||
|
||||
|
|
@ -1521,43 +1522,87 @@ _SESSION_PLAN_SURFACES: Final = (
|
|||
)
|
||||
|
||||
|
||||
async def _build_session_plan(logger, request_id, surface_kwargs=None, response=None):
|
||||
return await logger.async_build_agentic_loop_plan(
|
||||
tools={
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_1",
|
||||
"call_id": "c1",
|
||||
"name": LITELLM_CODE_EXECUTION_TOOL_NAME,
|
||||
"arguments": '{"code":"print(1)"}',
|
||||
}
|
||||
]
|
||||
},
|
||||
model="gpt-5",
|
||||
messages=[{"role": "user", "content": "x"}],
|
||||
response=response or FakeResponse(output=[_function_call_item()]),
|
||||
anthropic_messages_provider_config=None,
|
||||
anthropic_messages_optional_request_params={"tools": []},
|
||||
logging_obj=FakeLogging(litellm_call_id=request_id),
|
||||
stream=False,
|
||||
kwargs={
|
||||
"litellm_call_id": request_id,
|
||||
_SANDBOX_KEY: "conv-1",
|
||||
_SESSION_SCOPED_KEY: True,
|
||||
**(surface_kwargs or {}),
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(("surface_kwargs", "response"), _SESSION_PLAN_SURFACES)
|
||||
async def test_a_session_sandbox_whose_code_run_fails_is_not_reused_by_the_next_request(surface_kwargs, response):
|
||||
sandbox: Final = _SandboxThatCannotRunCode()
|
||||
logger: Final = CodeInterpreterInterceptionLogger(sandbox_config=sandbox)
|
||||
|
||||
for request_id in ("req1", "req2"):
|
||||
await logger.async_build_agentic_loop_plan(
|
||||
tools={
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_1",
|
||||
"call_id": "c1",
|
||||
"name": LITELLM_CODE_EXECUTION_TOOL_NAME,
|
||||
"arguments": '{"code":"print(1)"}',
|
||||
}
|
||||
]
|
||||
},
|
||||
model="gpt-5",
|
||||
messages=[{"role": "user", "content": "x"}],
|
||||
response=response,
|
||||
anthropic_messages_provider_config=None,
|
||||
anthropic_messages_optional_request_params={"tools": []},
|
||||
logging_obj=FakeLogging(litellm_call_id=request_id),
|
||||
stream=False,
|
||||
kwargs={
|
||||
"litellm_call_id": request_id,
|
||||
_SANDBOX_KEY: "conv-1",
|
||||
_SESSION_SCOPED_KEY: True,
|
||||
**surface_kwargs,
|
||||
},
|
||||
)
|
||||
await _build_session_plan(logger, "req1", surface_kwargs, response)
|
||||
await _build_session_plan(logger, "req2", surface_kwargs, response)
|
||||
|
||||
assert len(sandbox.create_calls) == 2
|
||||
assert len(sandbox.delete_calls) == 2
|
||||
|
||||
|
||||
class _SandboxWhoseFirstContainerDies(FakeSandbox):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.handles = []
|
||||
self.first_run_started = asyncio.Event()
|
||||
self.first_run_may_finish = asyncio.Event()
|
||||
|
||||
async def acreate_sandbox(self, **kwargs):
|
||||
self.create_calls.append(kwargs)
|
||||
handle = FakeHandle(sandbox_id=f"sbx_{len(self.handles)}")
|
||||
self.handles.append(handle)
|
||||
return handle
|
||||
|
||||
async def arun_code(self, *, container, code, **kwargs):
|
||||
self.run_calls.append({"container": container, "code": code})
|
||||
if len(self.run_calls) == 1:
|
||||
self.first_run_started.set()
|
||||
await self.first_run_may_finish.wait()
|
||||
if container is self.handles[0]:
|
||||
raise TimeoutError("sandbox expired")
|
||||
return CodeExecutionResult(stdout=self.stdout)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_a_late_failure_on_a_dead_session_sandbox_keeps_its_healthy_replacement():
|
||||
sandbox: Final = _SandboxWhoseFirstContainerDies()
|
||||
logger: Final = CodeInterpreterInterceptionLogger(sandbox_config=sandbox)
|
||||
|
||||
slow_request: Final = asyncio.create_task(_build_session_plan(logger, "req-slow"))
|
||||
await sandbox.first_run_started.wait()
|
||||
await _build_session_plan(logger, "req-fails-fast")
|
||||
await _build_session_plan(logger, "req-gets-replacement")
|
||||
sandbox.first_run_may_finish.set()
|
||||
await slow_request
|
||||
await _build_session_plan(logger, "req-after")
|
||||
|
||||
assert [call["container"] for call in sandbox.delete_calls] == [sandbox.handles[0]]
|
||||
assert [call["container"] for call in sandbox.run_calls[-2:]] == [sandbox.handles[1], sandbox.handles[1]]
|
||||
|
||||
|
||||
def _anthropic_message(content: list[dict[str, object]], stop_reason: str) -> dict[str, object]:
|
||||
return {
|
||||
"id": "msg_1",
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue