Skip to content

fix: rename Agent.run shared_tools kwarg to tools #2093

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
mikasenghaas merged 1 commit into from
Jul 21, 2026
Merged

fix: rename Agent.run shared_tools kwarg to tools #2093

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
16 changes: 7 additions & 9 deletions verifiers/v1/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,17 +221,17 @@ async def run(
task: Task,
*,
runtime: Runtime | None = None,
shared_tools: Mapping[str, SharedToolServer] | None = None,
tools: Mapping[str, SharedToolServer] | None = None,
) -> Trace:
"""Run this agent on `task` once and return the trace: `runtime` places it
into a live borrowed box instead of provisioning one; `shared_tools` are
live servers borrowed from their owner, counted in the pairing check.
into a live borrowed box instead of provisioning one; `tools` are live
servers borrowed from their owner, counted in the pairing check.
Retries whole while the trace ends with a retryable error (`config.retries`)
— never into a borrowed box; the final trace keeps earlier attempts' errors."""
retry = self.config.retries
history: list = []
for attempt in range(retry.max_retries + 1):
trace = await self._run_once(task, runtime, shared_tools)
trace = await self._run_once(task, runtime, tools)
if attempt == retry.max_retries or not trace_should_retry(trace, retry):
break
if runtime is not None:
Expand Down Expand Up @@ -363,7 +363,7 @@ class _EpisodeAgent(Agent):
they're created, finished ones land in `completed` (the episode's traces),
each run takes the eval's gate. The taskset's shared tool servers ride only
its own tasks — on an env-minted task they'd wrongly put MCP in play
(`shared_tools=` overrides)."""
(`tools=` overrides)."""

def __init__(
self,
Expand Down Expand Up @@ -414,15 +414,13 @@ async def run(
task: Task,
*,
runtime: Runtime | None = None,
shared_tools: Mapping[str, SharedToolServer] | None = None,
tools: Mapping[str, SharedToolServer] | None = None,
) -> Trace:
async with self._gate or nullcontext():
trace = await super().run(
task,
runtime=runtime,
shared_tools=shared_tools
if shared_tools is not None
else self._shared_for(task),
tools=tools if tools is not None else self._shared_for(task),
)
self._completed.append(trace)
return trace
Expand Down