mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-14 19:02:22 +02:00
GrzegorzandClaude Opus 5.5
afecd44ddf
ToolApprovalStore.create() sealed a process identity only from the request
authority's launch scopes, which exist only for granted bash/python. For an
ungranted call the sealing failed silently, so the approval was created
without a process identity and the executor always refused it ("Approved
action has no sealed process/job identity"). When the authority is not
inherited and has no launch scope for the backend, seal one in the
request's single workspace root at approval time, as filesystem approvals
already do. Inherited authorities still cannot widen.
The skill test run and audit arm left their `async for` over
stream_agent_loop early when an approval was needed, without closing the
generator. asyncio closed it later from another task, so its ContextVar
resets raised "Token ... was created in a different Context". Close the
stream with aclosing, like the scheduler and teacher escalation do.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
62 lines
2.5 KiB
Python
62 lines
2.5 KiB
Python
"""Skill test runs must close the agent stream in their own task (#6635).
|
|
|
|
When the agent asks for an exact approval, the skill test pauses by leaving its
|
|
`async for` over `stream_agent_loop`. The abandoned generator was later closed
|
|
by asyncio's finalizer in another task, so the ContextVar resets in its cleanup
|
|
(request_authority, turn_contract, ...) raised "Token ... was created in a
|
|
different Context". The stream must be closed before the run returns.
|
|
"""
|
|
import asyncio
|
|
import json
|
|
from contextvars import ContextVar
|
|
|
|
import routes.skills_routes as skills_routes
|
|
|
|
_BOUND: ContextVar = ContextVar("skill_test_bound", default=None)
|
|
|
|
_APPROVAL = {"kind": "tool_approval", "approval_id": "approval-1", "question": "Allow?"}
|
|
|
|
|
|
def _fake_stream(events, closed):
|
|
async def stream_agent_loop(*args, **kwargs):
|
|
token = _BOUND.set("bound")
|
|
try:
|
|
for event in events:
|
|
yield "data: " + json.dumps(event) + "\n\n"
|
|
yield "data: [DONE]\n\n"
|
|
finally:
|
|
# Raises ValueError when run from another task's context.
|
|
_BOUND.reset(token)
|
|
closed.append(asyncio.current_task())
|
|
return stream_agent_loop
|
|
|
|
|
|
async def test_paused_skill_test_closes_the_agent_stream_in_its_own_task(monkeypatch):
|
|
closed = []
|
|
events = [{"type": "tool_output", "output": "blocked", "ask_user": _APPROVAL},
|
|
{"delta": "never reached"}]
|
|
monkeypatch.setattr("src.agent_loop.stream_agent_loop", _fake_stream(events, closed))
|
|
key = ("alice", "demo")
|
|
skills_routes._skill_test_jobs[key] = {"log": [], "status": "running"}
|
|
try:
|
|
await skills_routes._run_skill_test_job(
|
|
key, "demo", "# skill", "task", "http://model.test", "m", {}, "alice")
|
|
job = skills_routes._skill_test_jobs[key]
|
|
assert job["status"] == "awaiting_approval"
|
|
assert closed == [asyncio.current_task()]
|
|
finally:
|
|
skills_routes._skill_test_jobs.pop(key, None)
|
|
|
|
|
|
async def test_audit_arm_closes_the_agent_stream_when_it_stops_for_approval(monkeypatch):
|
|
closed = []
|
|
events = [{"type": "tool_output", "output": "blocked", "ask_user": _APPROVAL},
|
|
{"delta": "never reached"}]
|
|
monkeypatch.setattr("src.agent_loop.stream_agent_loop", _fake_stream(events, closed))
|
|
|
|
_, _, approval = await skills_routes._run_skill_audit_arm(
|
|
[{"role": "user", "content": "task"}], "http://model.test", "m", {}, "alice")
|
|
|
|
assert approval == _APPROVAL
|
|
assert closed == [asyncio.current_task()]
|