Agentswarm/scripts/test-swarm-cross-review.py

"""Integration test for decentralized-rework P5: peer cross-review (#11).

>=2 independent peer reviewers replace the single-critic Master gate: disagreement is recorded,
the arbitrated verdict reopens rework targets, and each rework is attributed (root cause + who
introduced it). Hermetic, no model key.

Run from agent_swarm_v6 (install deps first — needs fakeredis):
    pip install -r orchestrator/requirements.txt -r agent/requirements.txt
    REDIS_FAKE=1 ENABLE_CROSS_REVIEW=1 python scripts/test-swarm-cross-review.py
"""
import asyncio
import os
import sys
from pathlib import Path

os.environ["REDIS_FAKE"] = "1"
os.environ["ENABLE_CROSS_REVIEW"] = "1"
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from orchestrator.redis_client import redis_client
from orchestrator import swarm_runtime as sr_mod
from orchestrator.swarm_runtime import swarm_runtime
from orchestrator.task_queue import task_queue, TaskStatus
from orchestrator import main as orch

failures = []


def check(name, cond):
    print(("PASS" if cond else "FAIL"), "-", name)
    if not cond:
        failures.append(name)


async def _noop(self, *a, **k):
    return None


async def completed_task(run, tid, agent):
    t = await task_queue.create_task(task_id=f"{run.swarm_id}-{tid}", description=tid,
                                     agent_role=tid.split("-")[-1], enqueue=False)
    t.status = TaskStatus.COMPLETED
    t.assigned_agent_id = agent
    await task_queue._save_task(t)
    await swarm_runtime.attach_task(run, t.task_id)
    return t


async def main():
    await redis_client.connect()
    sr_mod.SwarmRuntime._post_callback = _noop

    body = {"mode": "swarm", "requirement": {"objective": "cross review test"},
            "callback": {"url": "http://127.0.0.1:9/cb", "subscribed_events": []},
            "metadata": {"manager_deployment_id": "m-cr"}}
    run, _ = await swarm_runtime.get_or_create_run(body=body, idempotency_key=None, correlation_id="cr")
    impl = await completed_task(run, "t-implementation", "agent-impl")
    await completed_task(run, "t-documentation", "agent-doc")

    # two peers submit INDEPENDENT reviews of the implementation; they DISAGREE
    await orch.handle_review_decision("reviewer-1", {
        "task_id": impl.task_id, "verdict": "pass", "summary": "looks correct"})
    r = await orch.handle_review_decision("reviewer-2", {
        "task_id": impl.task_id, "verdict": "fail",
        "failed_criteria": ["implementation raises wrong exception"],
        "recommended_rework": [impl.task_id], "summary": "wrong exception on bad input"})
    check("two independent reviews recorded", r.get("review_count") == 2)

    # aggregate (called by the run lifecycle with a fresh run)
    fresh = await swarm_runtime.get_run(run.swarm_id)
    tasks = [await task_queue.get_task(tid) for tid in fresh.task_ids]
    reopened = await orch.run_cross_review(fresh, tasks)
    check("cross-review reopened rework target (rejected on split)", reopened is True)

    after = await swarm_runtime.get_run(run.swarm_id)
    cr = after.metadata.get("cross_review") or {}
    check("verdict recorded with disagreement", cr.get("disagreement") is True and cr.get("accepted") is False)
    check("split arbitrated by majority → reject (safety bias)",
          cr.get("method") == "majority" and cr.get("pass_votes") == 1 and cr.get("fail_votes") == 1)
    impl_after = await task_queue.get_task(impl.task_id)
    check("flagged task reopened to PENDING", impl_after.status == TaskStatus.PENDING)
    attrs = after.metadata.get("rework_attributions") or []
    check("rework attributed (root cause + detector)",
          attrs and attrs[0]["target_task_id"] == impl.task_id
          and attrs[0]["root_cause"] in {"implementation", "collaboration"}
          and attrs[0]["detected_by_agent_id"] == "reviewer-2")
    check("reviews consumed after the cycle", not after.metadata.get("reviews"))
    check("review cycle counter advanced", after.metadata.get("review_cycles") == 1)

    # --- unanimous pass → accept, no reopen ---
    run2, _ = await swarm_runtime.get_or_create_run(
        body={**body, "metadata": {"manager_deployment_id": "m-cr2"}}, idempotency_key=None, correlation_id="cr2")
    a2 = await completed_task(run2, "t-implementation", "agent-impl")
    for rid in ("reviewer-1", "reviewer-2"):
        await orch.handle_review_decision(rid, {"task_id": a2.task_id, "verdict": "pass", "summary": "ok"})
    fresh2 = await swarm_runtime.get_run(run2.swarm_id)
    reopened2 = await orch.run_cross_review(fresh2, [await task_queue.get_task(t) for t in fresh2.task_ids])
    check("unanimous pass → not reopened", reopened2 is False)
    a2_after = await task_queue.get_task(a2.task_id)
    check("accepted task stays COMPLETED", a2_after.status == TaskStatus.COMPLETED)

    # --- single reviewer is NOT a cross-review (needs >=2) ---
    run3, _ = await swarm_runtime.get_or_create_run(
        body={**body, "metadata": {"manager_deployment_id": "m-cr3"}}, idempotency_key=None, correlation_id="cr3")
    a3 = await completed_task(run3, "t-implementation", "agent-impl")
    await orch.handle_review_decision("reviewer-1", {"task_id": a3.task_id, "verdict": "fail",
                                                     "recommended_rework": [a3.task_id]})
    fresh3 = await swarm_runtime.get_run(run3.swarm_id)
    reopened3 = await orch.run_cross_review(fresh3, [await task_queue.get_task(t) for t in fresh3.task_ids])
    check("single reviewer → no cross-review (needs >=2)", reopened3 is False)

    print()
    if failures:
        print(f"{len(failures)} cross-review (P5) check(s) FAILED: {failures}")
        sys.exit(1)
    print("all swarm cross-review (P5) checks passed")


if __name__ == "__main__":
    asyncio.run(main())