Agentswarm/scripts/test-contract-freeze.py

"""Contract-freeze tests (agent_swarm#14 / #15) for the Manager/client query contract.

Verifies the frozen Swarm->Manager callback contract that the desktop "task cockpit"
(heicode-mananger #28/#45/#46) consumes:
  * every event envelope carries a per-swarm strictly-increasing, gap-free `sequence` (#15.1);
  * the 13 frozen client-facing event types exist and round-trip with a sequence (#15.2);
  * approval.approved/rejected fire from the real approval-decision site (#15.2);
  * swarm.stopped fires from the real stop site; swarm.completed/failed are defined (#15.2);
  * artifact.created carries the flat {uri, checksum, task_id, created_at} shape (#15.4);
  * secret_ref/credential_ref pass through as azkv refs but plaintext creds are redacted (#15.3).

Hermetic: REDIS_FAKE, no model key, no real Manager callback (callback url empty).

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

os.environ["REDIS_FAKE"] = "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, FROZEN_CLIENT_EVENT_TYPES

failures = []


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


async def stored_events(swarm_id):
    raw = await redis_client.lrange(f"{swarm_runtime.EVENT_KEY_PREFIX}{swarm_id}", 0, -1)
    return [json.loads(r) for r in raw]


async def new_run(objective="freeze test"):
    body = {"mode": "swarm", "orchestration_plan": {"objective": objective},
            # no callback url -> nothing is POSTed; events are still stored locally
            "callback": {"url": "", "subscribed_events": []},
            "metadata": {"manager_deployment_id": "m-freeze"}}
    run, _ = await swarm_runtime.get_or_create_run(body=body, idempotency_key=None, correlation_id="cf")
    return run


async def test_sequence_monotonic():
    run = await new_run()
    for i in range(5):
        await swarm_runtime.emit_event(run, "task.running", task_id=f"t{i}", payload={"agent_role": "impl"})
    evs = await stored_events(run.swarm_id)
    seqs = [e.get("sequence") for e in evs]
    check("every event carries a sequence", all(isinstance(s, int) for s in seqs))
    check("sequence starts at 1 and is gap-free/increasing", seqs == list(range(1, len(seqs) + 1)))

    # A second run has its OWN sequence space starting at 1 (per-swarm, not global).
    run2 = await new_run()
    await swarm_runtime.emit_event(run2, "task.running", task_id="x", payload={"agent_role": "impl"})
    evs2 = await stored_events(run2.swarm_id)
    check("sequence is per-swarm (second run restarts at 1)", evs2[0]["sequence"] == 1)


async def test_frozen_event_types_roundtrip():
    # The #28 freeze defined these 13 core client types; #34 later added 4 review/rework types
    # (review.started/decision_made, rework.requested/completed). Assert the 13 core are present
    # (subset), not an exact count, so adding client events doesn't break this contract test.
    expected = {
        "task.created", "task.claimed", "task.running", "task.completed", "task.failed",
        "handoff.created", "approval.requested", "approval.approved", "approval.rejected",
        "artifact.created", "swarm.completed", "swarm.failed", "swarm.stopped",
    }
    check("the 13 #28-core client types are all in the frozen set", expected.issubset(set(FROZEN_CLIENT_EVENT_TYPES)))

    run = await new_run()
    for et in FROZEN_CLIENT_EVENT_TYPES:
        await swarm_runtime.emit_event(run, et, payload={"status": "x"})
    evs = await stored_events(run.swarm_id)
    types = [e["event_type"] for e in evs]
    # The run also emits deployment.status_changed on creation; assert the frozen 13 are all present.
    check("all 13 frozen types round-trip with an envelope", expected.issubset(set(types)))
    check("every frozen-type envelope has a sequence", all(isinstance(e["sequence"], int) for e in evs))


async def test_artifact_shape():
    run = await new_run()
    await swarm_runtime.emit_event(
        run, "artifact.created", task_id="t-art",
        artifact={"artifact_id": "art_1", "uri": "git://repo#main", "checksum": "abc123",
                  "size_bytes": 42},
    )
    ev = (await stored_events(run.swarm_id))[-1]
    p = ev["payload"]
    check("artifact payload has uri/checksum", p.get("uri") == "git://repo#main" and p.get("checksum") == "abc123")
    check("artifact task_id defaulted from event task_id", p.get("task_id") == "t-art")
    check("artifact created_at defaulted to event time", bool(p.get("created_at")))
    check("artifact size_bytes preserved when known", p.get("size_bytes") == 42)

    # size unknown -> NOT fabricated (rule #9)
    run2 = await new_run()
    await swarm_runtime.emit_event(run2, "artifact.created", task_id="t2",
                                   artifact={"artifact_id": "art_2", "uri": "runtime://x", "checksum": "d"})
    p2 = (await stored_events(run2.swarm_id))[-1]["payload"]
    check("unknown size_bytes is omitted, not faked", "size_bytes" not in p2)


async def test_approval_and_stop_sites():
    # approval.approved from the real decision site
    run = await new_run()
    run.approvals["ap1"] = {"approval_id": "ap1"}
    await swarm_runtime.save_run(run)
    await swarm_runtime.record_approval_decision(run.swarm_id, "ap1", {"decision": "approved"})
    types = [e["event_type"] for e in await stored_events(run.swarm_id)]
    check("approval.approved emitted on approve", "approval.approved" in types)

    run2 = await new_run()
    run2.approvals["ap2"] = {"approval_id": "ap2"}
    await swarm_runtime.save_run(run2)
    await swarm_runtime.record_approval_decision(run2.swarm_id, "ap2", {"decision": "rejected", "reason": "no"})
    types2 = [e["event_type"] for e in await stored_events(run2.swarm_id)]
    check("approval.rejected emitted on reject", "approval.rejected" in types2)

    # swarm.stopped from the real stop site
    run3 = await new_run()
    await swarm_runtime.stop_run(run3.deployment_id, reason="manager stop")
    ev3 = await stored_events(run3.swarm_id)
    check("swarm.stopped emitted on stop_run", "swarm.stopped" in [e["event_type"] for e in ev3])
    stopped = [e for e in ev3 if e["event_type"] == "swarm.stopped"][0]
    check("swarm.stopped payload status=stopped", stopped["payload"].get("status") == "stopped")


async def test_redaction():
    run = await new_run()
    await swarm_runtime.emit_event(run, "approval.requested", payload={
        "approval_id": "ap",
        "secret_ref": "azkv://vault/secrets/x",   # azkv reference: passes through (not plaintext)
        "access_token": "PLAINTEXT-SHOULD-VANISH",
    })
    p = (await stored_events(run.swarm_id))[-1]["payload"]
    check("secret_ref (azkv ref) passes through for HM to strip", p.get("secret_ref") == "azkv://vault/secrets/x")
    check("plaintext access_token is redacted", p.get("access_token") == "[redacted]")


async def main():
    await redis_client.connect()
    await test_sequence_monotonic()
    await test_frozen_event_types_roundtrip()
    await test_artifact_shape()
    await test_approval_and_stop_sites()
    await test_redaction()
    print()
    if failures:
        print(f"{len(failures)} contract-freeze check(s) FAILED: {failures}")
        sys.exit(1)
    print("all contract-freeze checks passed")


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