mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
feat(sandbox): on-demand provisioning via request_sandbox verb (#338)
* feat(sandbox): on-demand request_sandbox verb replaces eager provisioning Sandboxes were provisioned at every agent spawn for opted-in projects, so every role paid the sidecar spin-up and a provisioning failure refused the spawn. Provisioning now happens when an agent asks: the request_sandbox do-verb (dev + QA) reaches the orchestrator through ContentActionsDeps, ensure_sandbox provisions idempotently with an in-memory per-agent cache (evicted at teardown and janitor sweep), and creds return in the envelope payload including ready-to-export ROBOCO_TEST_* values. Spawn now only injects a marker env naming the available services plus a briefing line; sandbox failures can no longer refuse a spawn. Teardown lifecycle unchanged. * feat(sandbox): harden request_sandbox + Phase 3 wiring proof and docs Hardening from adversarial review: ensure_sandbox now provisions the project's full opted-in set on first request (a later superset can never tear down a live sandbox mid-use), serializes per-agent behind an asyncio lock (a client timeout-retry no longer races its own in-flight provision), and verifies container liveness on every cache hit (a dead sandbox evicts and re-provisions instead of serving dead creds). MCP client budget 720->1080s for the full-set cold case. Phase 3: e2e smoke wiring test (manifest grants + guard-chain envelopes over the real API), sandbox-db/tools/map docs and CLAUDE.md rewritten for on-demand. * feat(sandbox): release sandboxes when the agent's work ends CEO directive: sidecars must not dangle once the agent is done. The six work-ending verbs (i_am_done, unclaim, i_am_idle, pass_review, fail_review, i_documented) now release the caller's sandbox best-effort on their success path via release_sandbox (lock + teardown + cache evict; a no-sandbox agent costs a dict lookup). Container removal and the janitor remain the backstop; a re-request provisions fresh. * test(sandbox): monkeypatch the release hook instead of method assignment mypy method-assign rejected the direct AsyncMock assignments; the prior static gate ran before this test file landed. * test(sandbox): guard envelope evidence for mypy in verb tests * chore(prompts): regenerate verb tables for request_sandbox * chore: resolve merge with master (breadcrumbs + statement budget) --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
Renzo F
@@ -0,0 +1,289 @@
|
||||
"""ContentActions.request_sandbox — the on-demand sandbox DB/Redis/Mongo verb.
|
||||
|
||||
Guard matrix (flag off / no active task / no project / not opted in / subset
|
||||
violation / orchestrator unavailable), the success envelope payload shape, and
|
||||
cross-agent isolation (ensure_sandbox is always called with the CALLER's own
|
||||
resolved slug, never another agent's).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from unittest.mock import AsyncMock, MagicMock
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from roboco.config import settings
|
||||
from roboco.models.sandbox import SandboxConnection, SandboxInfo
|
||||
from roboco.runtime.sandbox import SandboxProvisionError
|
||||
from roboco.services.gateway.content_actions import ContentActions, ContentActionsDeps
|
||||
|
||||
|
||||
def _make_actions(
|
||||
*,
|
||||
task_obj: MagicMock | None,
|
||||
orchestrator: AsyncMock | None,
|
||||
) -> tuple[ContentActions, MagicMock]:
|
||||
task = AsyncMock()
|
||||
task.get_active_task_for_agent.return_value = task_obj
|
||||
task.session = MagicMock()
|
||||
deps = ContentActionsDeps(
|
||||
task=task,
|
||||
git=MagicMock(),
|
||||
a2a=MagicMock(),
|
||||
journal=MagicMock(),
|
||||
workspace=MagicMock(),
|
||||
notifications=MagicMock(),
|
||||
orchestrator=orchestrator,
|
||||
)
|
||||
return ContentActions(deps), task
|
||||
|
||||
|
||||
def _task(project_id: object | None = uuid4()) -> MagicMock:
|
||||
t = MagicMock()
|
||||
t.id = uuid4()
|
||||
t.project_id = project_id
|
||||
t.status = "in_progress"
|
||||
return t
|
||||
|
||||
|
||||
def _stub_project(monkeypatch: pytest.MonkeyPatch, services: list[str] | None) -> None:
|
||||
project = MagicMock(sandbox_services=services)
|
||||
project_service = MagicMock()
|
||||
project_service.get = AsyncMock(return_value=project)
|
||||
monkeypatch.setattr(
|
||||
"roboco.services.project.get_project_service", lambda _s: project_service
|
||||
)
|
||||
|
||||
|
||||
def _sandbox_info() -> SandboxInfo:
|
||||
return SandboxInfo(
|
||||
services={
|
||||
"postgres": SandboxConnection(
|
||||
host="roboco-sandbox-pg-dev-1",
|
||||
port=5432,
|
||||
password="pw",
|
||||
user="sandbox",
|
||||
database="sandbox",
|
||||
)
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Guard matrix
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_flag_off_refuses_before_task_lookup(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", False)
|
||||
actions, task = _make_actions(task_obj=None, orchestrator=None)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
task.get_active_task_for_agent.assert_not_awaited()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_active_task_refused(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
actions, _task_svc = _make_actions(task_obj=None, orchestrator=None)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
assert "give_me_work" in (env.remediate or "")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_task_without_project_refused(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
actions, _task_svc = _make_actions(
|
||||
task_obj=_task(project_id=None), orchestrator=None
|
||||
)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_project_not_opted_in_refused(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=None)
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=None)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
assert "not opted" in (env.message or "")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_requested_service_outside_opted_set_names_allowed_set(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres"])
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=None)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4(), services=["redis"])
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
assert "postgres" in (env.remediate or "")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_orchestrator_unavailable_is_retryable(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres"])
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=None)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
assert "retry" in (env.remediate or "").lower()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_provision_failure_surfaces_as_retryable_invalid_state(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.side_effect = SandboxProvisionError("image pull failed")
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
assert "provisioning failed" in (env.message or "")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Success path — envelope payload shape
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_success_returns_creds_in_evidence_with_env_subdict(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.return_value = _sandbox_info()
|
||||
actions, task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
expected_port = 5432
|
||||
assert env.error is None
|
||||
assert env.evidence is not None
|
||||
payload = env.evidence["postgres"]
|
||||
assert payload["host"] == "roboco-sandbox-pg-dev-1"
|
||||
assert payload["port"] == expected_port
|
||||
assert payload["user"] == "sandbox"
|
||||
assert payload["password"] == "pw"
|
||||
assert payload["database"] == "sandbox"
|
||||
assert payload["env"]["ROBOCO_TEST_DB_HOST"] == "roboco-sandbox-pg-dev-1"
|
||||
assert payload["env"]["ROBOCO_TEST_DB_PASSWORD"] == "pw"
|
||||
task_svc.heartbeat.assert_awaited_once()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_omitted_services_requests_full_opted_set(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres", "redis"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.return_value = _sandbox_info()
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
await actions.request_sandbox(agent_id=uuid4())
|
||||
|
||||
orch.ensure_sandbox.assert_awaited_once()
|
||||
called_services = orch.ensure_sandbox.call_args.args[1]
|
||||
assert sorted(called_services) == ["postgres", "redis"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_ensure_sandbox_called_with_full_opted_set_not_just_requested(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""DEFECT 1 fix: the verb always passes the project's whole opted-in set
|
||||
(not just this call's ``services`` subset) as ensure_sandbox's ``opted``
|
||||
argument, so a superset request later in the session can never trigger a
|
||||
fresh provision() that tears down the agent's live sandbox."""
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres", "redis"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.return_value = _sandbox_info()
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
await actions.request_sandbox(agent_id=uuid4(), services=["postgres"])
|
||||
|
||||
called_requested = orch.ensure_sandbox.call_args.args[1]
|
||||
called_opted = orch.ensure_sandbox.call_args.args[2]
|
||||
assert called_requested == ["postgres"]
|
||||
assert sorted(called_opted) == ["postgres", "redis"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_response_payload_filtered_to_requested_services(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""`ensure_sandbox` provisions the full opted set under the hood; the
|
||||
verb's response only surfaces what THIS call actually asked for."""
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres", "redis"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.return_value = SandboxInfo(
|
||||
services={
|
||||
"postgres": SandboxConnection(
|
||||
host="h", port=5432, password="pw", user="sandbox", database="sandbox"
|
||||
),
|
||||
"redis": SandboxConnection(host="h", port=6379, password="rw"),
|
||||
}
|
||||
)
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
env = await actions.request_sandbox(agent_id=uuid4(), services=["postgres"])
|
||||
|
||||
assert env.error is None
|
||||
assert env.evidence is not None
|
||||
assert set(env.evidence) == {"postgres"}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Cross-agent isolation
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_ensure_sandbox_keyed_off_caller_own_slug(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""Two different callers resolve to two different ensure_sandbox slugs —
|
||||
a caller can never reach another agent's cached sandbox."""
|
||||
monkeypatch.setattr(settings, "sandbox_db_enabled", True)
|
||||
_stub_project(monkeypatch, services=["postgres"])
|
||||
orch = AsyncMock()
|
||||
orch.ensure_sandbox.return_value = _sandbox_info()
|
||||
actions, _task_svc = _make_actions(task_obj=_task(), orchestrator=orch)
|
||||
|
||||
agent_a, agent_b = uuid4(), uuid4()
|
||||
await actions.request_sandbox(agent_id=agent_a)
|
||||
await actions.request_sandbox(agent_id=agent_b)
|
||||
|
||||
slugs_called = [c.args[0] for c in orch.ensure_sandbox.call_args_list]
|
||||
assert slugs_called[0] != slugs_called[1]
|
||||
assert slugs_called[0] == str(agent_a)
|
||||
assert slugs_called[1] == str(agent_b)
|
||||
@@ -0,0 +1,513 @@
|
||||
"""Sandbox release hook — Choreographer._teardown_sandbox_best_effort.
|
||||
|
||||
CEO directive: sandboxes must die when an agent's engagement with its work
|
||||
ends, not only when its container is removed. Ties the on-demand
|
||||
request_sandbox subsystem's teardown to the SUCCESSFUL exit of the six
|
||||
verbs whose completion means exactly that: i_am_done, unclaim, i_am_idle,
|
||||
pass_review, fail_review, i_documented. A rejected/failed verb call must
|
||||
NOT release (the work isn't done), and a release failure must never fail
|
||||
the verb — best-effort, backstopped by the container-removal teardown +
|
||||
janitor sweep that already exist.
|
||||
|
||||
Two layers:
|
||||
- the helper itself (`_teardown_sandbox_best_effort`), tested directly
|
||||
against a fake orchestrator;
|
||||
- the six call sites, tested by spying on the helper (patched onto the
|
||||
instance) so each verb's fixture stays the minimal one already proven
|
||||
by its own dedicated test file (test_choreographer_dev.py,
|
||||
test_unclaim.py, test_choreographer_idle_guards.py,
|
||||
test_choreographer_qa.py, test_choreographer_doc.py).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import UTC, datetime
|
||||
from typing import Any
|
||||
from unittest.mock import AsyncMock, MagicMock
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
||||
from structlog.testing import capture_logs
|
||||
|
||||
|
||||
def _make_deps(**overrides: Any) -> ChoreographerDeps:
|
||||
base: dict[str, Any] = {
|
||||
"task": AsyncMock(),
|
||||
"work_session": AsyncMock(),
|
||||
"git": AsyncMock(),
|
||||
"a2a": AsyncMock(),
|
||||
"journal": AsyncMock(),
|
||||
"audit": AsyncMock(),
|
||||
"evidence_repo": AsyncMock(),
|
||||
}
|
||||
base.update(overrides)
|
||||
task = base["task"]
|
||||
# Covers both VerbRunner's savepoint (i_am_done/pass_review/fail_review/
|
||||
# i_documented) and i_documented's own session.flush() — one shared
|
||||
# setup for every verb exercised in this file.
|
||||
task.session = MagicMock()
|
||||
task.session.begin_nested = MagicMock(
|
||||
return_value=MagicMock(
|
||||
__aenter__=AsyncMock(return_value=None),
|
||||
__aexit__=AsyncMock(return_value=False),
|
||||
)
|
||||
)
|
||||
task.session.flush = AsyncMock()
|
||||
repo = base["evidence_repo"]
|
||||
for method in (
|
||||
"list_unread_a2a",
|
||||
"list_unread_mentions",
|
||||
"list_pending_notifications",
|
||||
"task_metadata_gaps",
|
||||
"recent_team_activity",
|
||||
"blockers_in_lane",
|
||||
"journal_highlights_for_task",
|
||||
):
|
||||
getattr(repo, method).return_value = []
|
||||
_ldef = base["journal"].latest_decision_at.return_value
|
||||
if type(_ldef).__name__ in ("MagicMock", "AsyncMock"):
|
||||
base["journal"].latest_decision_at.return_value = datetime.now(UTC)
|
||||
return ChoreographerDeps(**base)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# The helper itself
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_helper_noop_when_orchestrator_missing() -> None:
|
||||
c = Choreographer(_make_deps()) # orchestrator defaults to None
|
||||
|
||||
await c._teardown_sandbox_best_effort(uuid4()) # must not raise
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_helper_calls_release_sandbox_with_resolved_slug() -> None:
|
||||
agent_id = uuid4()
|
||||
orch = AsyncMock()
|
||||
c = Choreographer(_make_deps(orchestrator=orch))
|
||||
|
||||
await c._teardown_sandbox_best_effort(agent_id)
|
||||
|
||||
# Not seeded in AGENT_UUIDS, so _resolve_to_slug falls back to identity —
|
||||
# mirrors test_request_sandbox_verb.py's cross-agent-isolation assertion.
|
||||
orch.release_sandbox.assert_awaited_once_with(str(agent_id))
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_helper_swallows_release_failure_and_logs() -> None:
|
||||
agent_id = uuid4()
|
||||
orch = AsyncMock()
|
||||
orch.release_sandbox.side_effect = RuntimeError("docker down")
|
||||
c = Choreographer(_make_deps(orchestrator=orch))
|
||||
|
||||
with capture_logs() as logs:
|
||||
await c._teardown_sandbox_best_effort(agent_id) # must not raise
|
||||
|
||||
assert any("sandbox_release_failed" in str(e.get("event", "")) for e in logs)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# i_am_done
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _ready_i_am_done_task(task_id: Any, agent_id: Any, **overrides: Any) -> MagicMock:
|
||||
base = {
|
||||
"id": task_id,
|
||||
"status": "in_progress",
|
||||
"assigned_to": agent_id,
|
||||
"plan": {"x": 1},
|
||||
"branch_name": "feature/backend/abc",
|
||||
"work_session_id": uuid4(),
|
||||
"self_verified": False,
|
||||
"pr_number": 8,
|
||||
"pr_url": "https://x/pr/8",
|
||||
"team": "backend",
|
||||
"progress_updates": [{"message": "did x"}],
|
||||
"acceptance_criteria": [],
|
||||
"acceptance_criteria_status": [],
|
||||
"commits": [{"sha": "deadbeef"}],
|
||||
"documents": [],
|
||||
"dev_notes": "Implemented the change and added tests covering the new path.",
|
||||
"quick_context": None,
|
||||
}
|
||||
base.update(overrides)
|
||||
return MagicMock(**base)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_done_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = _ready_i_am_done_task(task_id, agent_id)
|
||||
after_verify = MagicMock(
|
||||
**{**t.__dict__, "self_verified": True, "status": "verifying"}
|
||||
)
|
||||
after_submit = MagicMock(**{**after_verify.__dict__, "status": "awaiting_qa"})
|
||||
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.agent_for.return_value = MagicMock(
|
||||
id=agent_id, role="developer", team="backend", slug=None
|
||||
)
|
||||
task_svc.submit_verification.return_value = after_verify
|
||||
task_svc.submit_qa.return_value = after_submit
|
||||
task_svc.qa_agent_for_team.return_value = MagicMock(
|
||||
id=uuid4(), skills=[{"id": "code_review"}]
|
||||
)
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_reflect_for_task.return_value = True
|
||||
journal_svc.has_decision_for_task.return_value = True
|
||||
journal_svc.has_learning_for_task.return_value = False
|
||||
journal_svc.has_struggle_for_task.return_value = False
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_am_done(agent_id, task_id, "done")
|
||||
|
||||
assert env.error is None
|
||||
release.assert_awaited_once_with(agent_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_done_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = None
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_am_done(agent_id, task_id, "done")
|
||||
|
||||
assert env.error == "not_found"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# unclaim
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_unclaim_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = MagicMock(id=task_id, status="claimed", assigned_to=agent_id)
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.agent_for.return_value = MagicMock(
|
||||
id=agent_id, role="developer", team="backend", slug=None
|
||||
)
|
||||
task_svc.unclaim_for_agent.return_value = MagicMock(
|
||||
id=task_id, status="pending", assigned_to=None
|
||||
)
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.unclaim(agent_id, task_id)
|
||||
|
||||
assert env.error is None
|
||||
release.assert_awaited_once_with(agent_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_unclaim_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = None
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.unclaim(agent_id, task_id)
|
||||
|
||||
assert env.error == "not_found"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# i_am_idle
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_idle_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.list_assigned_for_agent.return_value = []
|
||||
task_svc.list_in_progress_for_agent.return_value = []
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_am_idle(agent_id)
|
||||
|
||||
assert env.error is None
|
||||
assert env.status == "idle"
|
||||
release.assert_awaited_once_with(agent_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_idle_with_unread_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""idle_with_unread sends the agent back to work — not a real exit, so
|
||||
the container does not shut down and the sandbox must survive."""
|
||||
agent_id = uuid4()
|
||||
deps = _make_deps()
|
||||
deps.evidence_repo.list_unread_a2a.return_value = [{"from": "x", "task_id": "t1"}]
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_am_idle(agent_id)
|
||||
|
||||
assert env.status == "idle_with_unread"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_idle_guard_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
agent_id = uuid4()
|
||||
pending = MagicMock(id=uuid4(), status="pending")
|
||||
task_svc = AsyncMock()
|
||||
task_svc.list_assigned_for_agent.return_value = [pending]
|
||||
task_svc.list_in_progress_for_agent.return_value = []
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_am_idle(agent_id)
|
||||
|
||||
assert env.error == "invalid_state"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# pass_review / fail_review
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _qa_owned_task(task_id: Any, qa_id: Any, **overrides: Any) -> MagicMock:
|
||||
base = {
|
||||
"id": task_id,
|
||||
"status": "awaiting_qa",
|
||||
"task_type": "code",
|
||||
"team": "backend",
|
||||
"assigned_to": qa_id,
|
||||
"qa_evidence_inspected": True,
|
||||
"quick_context": None,
|
||||
}
|
||||
base.update(overrides)
|
||||
return MagicMock(**base)
|
||||
|
||||
|
||||
def _qa_agent_mock(qa_id: Any) -> MagicMock:
|
||||
return MagicMock(id=qa_id, role="qa", team="backend", slug=None)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_pass_review_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
qa_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = _qa_owned_task(task_id, qa_id)
|
||||
after = MagicMock(
|
||||
id=task_id,
|
||||
status="awaiting_documentation",
|
||||
assigned_to=qa_id,
|
||||
team="backend",
|
||||
pr_url="https://x/pr/8",
|
||||
qa_evidence_inspected=True,
|
||||
)
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.agent_for.return_value = _qa_agent_mock(qa_id)
|
||||
task_svc.qa_pass.return_value = after
|
||||
task_svc.documenter_for_team.return_value = MagicMock(id=uuid4())
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_learning_for_task.return_value = True
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
notes = (
|
||||
"Reviewed PR carefully. Branch convention correct. Commit prefix "
|
||||
"verified. README diff matches spec. All acceptance criteria met."
|
||||
)
|
||||
env = await c.pass_review(qa_id, task_id, notes=notes)
|
||||
|
||||
assert env.error is None
|
||||
release.assert_awaited_once_with(qa_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_pass_review_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
qa_id = uuid4()
|
||||
task_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = None
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.pass_review(qa_id, task_id, notes="x")
|
||||
|
||||
assert env.error == "not_found"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fail_review_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
qa_id = uuid4()
|
||||
task_id = uuid4()
|
||||
dev_id = uuid4()
|
||||
t = _qa_owned_task(task_id, qa_id)
|
||||
after = MagicMock(
|
||||
id=task_id,
|
||||
status="needs_revision",
|
||||
assigned_to=dev_id,
|
||||
team="backend",
|
||||
)
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.agent_for.return_value = _qa_agent_mock(qa_id)
|
||||
task_svc.qa_fail.return_value = after
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_learning_for_task.return_value = True
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
issues = [
|
||||
"Missing unit test coverage for /healthz endpoint — add an assertion",
|
||||
"Lint errors in /api/foo.py: unused import and missing return type",
|
||||
]
|
||||
env = await c.fail_review(qa_id, task_id, issues)
|
||||
|
||||
assert env.error is None
|
||||
release.assert_awaited_once_with(qa_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fail_review_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
qa_id = uuid4()
|
||||
task_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = None
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.fail_review(qa_id, task_id, ["some issue"])
|
||||
|
||||
assert env.error == "not_found"
|
||||
release.assert_not_awaited()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# i_documented
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _doc_owned_task(task_id: Any, doc_id: Any, **overrides: Any) -> MagicMock:
|
||||
base = {
|
||||
"id": task_id,
|
||||
"status": "awaiting_documentation",
|
||||
"task_type": "code",
|
||||
"team": "backend",
|
||||
"assigned_to": doc_id,
|
||||
"quick_context": None,
|
||||
}
|
||||
base.update(overrides)
|
||||
return MagicMock(**base)
|
||||
|
||||
|
||||
def _doc_agent_mock(doc_id: Any) -> MagicMock:
|
||||
return MagicMock(id=doc_id, role="documenter", team="backend", slug=None)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_documented_success_releases_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
doc_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = _doc_owned_task(task_id, doc_id)
|
||||
after = MagicMock(
|
||||
id=task_id, status="awaiting_pm_review", assigned_to=doc_id, team="backend"
|
||||
)
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.agent_for.return_value = _doc_agent_mock(doc_id)
|
||||
task_svc.docs_complete.return_value = after
|
||||
task_svc.cell_pm_for_team.return_value = MagicMock(id=uuid4())
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_reflect_for_task.return_value = True
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
notes = "Wrote backend/guides/feature-x.md with usage examples and config notes."
|
||||
files = ["backend/guides/feature-x.md"]
|
||||
env = await c.i_documented(doc_id, task_id, notes=notes, files=files)
|
||||
|
||||
assert env.error is None
|
||||
release.assert_awaited_once_with(doc_id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_documented_rejection_does_not_release_sandbox(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
doc_id = uuid4()
|
||||
task_id = uuid4()
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = None
|
||||
deps = _make_deps(task=task_svc)
|
||||
c = Choreographer(deps)
|
||||
release = AsyncMock()
|
||||
monkeypatch.setattr(c, "_teardown_sandbox_best_effort", release)
|
||||
|
||||
env = await c.i_documented(doc_id, task_id, notes="x" * 30, files=["docs.md"])
|
||||
|
||||
assert env.error == "not_found"
|
||||
release.assert_not_awaited()
|
||||
Reference in New Issue
Block a user