Skip to content

Support tau-bench environment idle TTL #704

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bradhilton merged 1 commit into from
Jun 2, 2026
+37 −0
Merged

Support tau-bench environment idle TTL #704

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions src/art/tau_bench/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,7 @@ async def create_environment(
user_llm_args: dict[str, Any] | None = None,
retrieval_config: str | None = None,
retrieval_config_kwargs: dict[str, Any] | None = None,
idle_timeout_seconds: float | None = None,
) -> EnvironmentResponse:
response = await self._request(
"POST",
Expand All @@ -197,6 +198,7 @@ async def create_environment(
"user_llm_args": user_llm_args,
"retrieval_config": retrieval_config,
"retrieval_config_kwargs": retrieval_config_kwargs,
"idle_timeout_seconds": idle_timeout_seconds,
}.items()
if value is not None
},
Expand Down Expand Up @@ -238,6 +240,7 @@ async def environment(
user_llm_args: dict[str, Any] | None = None,
retrieval_config: str | None = None,
retrieval_config_kwargs: dict[str, Any] | None = None,
idle_timeout_seconds: float | None = None,
) -> AsyncGenerator[EnvironmentResponse, None]:
env = await self.create_environment(
domain=domain,
Expand All @@ -246,6 +249,7 @@ async def environment(
user_llm_args=user_llm_args,
retrieval_config=retrieval_config,
retrieval_config_kwargs=retrieval_config_kwargs,
idle_timeout_seconds=idle_timeout_seconds,
)
try:
yield env
Expand Down
33 changes: 33 additions & 0 deletions tests/unit/test_tau_bench_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,37 @@ async def handler(request: httpx.Request) -> httpx.Response:
assert attempts == 3


@pytest.mark.asyncio
async def test_client_sends_create_environment_idle_timeout() -> None:
seen: dict[str, Any] = {}

async def handler(request: httpx.Request) -> httpx.Response:
seen["json"] = json.loads(request.content)
return httpx.Response(
200,
json={"id": "env-1", "observation": "user: hello", "info": {}},
)

http_client = httpx.AsyncClient(
base_url="http://tau.test",
transport=httpx.MockTransport(handler),
)
client = TauBenchClient(api_key="secret", http_client=http_client)
await client.create_environment(
domain="telecom",
task_id="task_001",
idle_timeout_seconds=120,
)
await client.close()
await http_client.aclose()

assert seen["json"] == {
"domain": "telecom",
"task_id": "task_001",
"idle_timeout_seconds": 120,
}


@pytest.mark.asyncio
async def test_module_default_client_can_be_replaced(
monkeypatch: pytest.MonkeyPatch,
Expand Down Expand Up @@ -182,6 +213,7 @@ async def create_environment(
user_llm_args: dict[str, Any] | None = None,
retrieval_config: str | None = None,
retrieval_config_kwargs: dict[str, Any] | None = None,
idle_timeout_seconds: float | None = None,
) -> EnvironmentResponse:
self.create_kwargs = {
"domain": domain,
Expand All @@ -190,6 +222,7 @@ async def create_environment(
"user_llm_args": user_llm_args,
"retrieval_config": retrieval_config,
"retrieval_config_kwargs": retrieval_config_kwargs,
"idle_timeout_seconds": idle_timeout_seconds,
}
return EnvironmentResponse(
id="env-1",
Expand Down
Loading