feat(clustering): campaign-clusterer worker + bus topics + CLI

The campaign clusterer worker mirrors the identity-side worker shell
(bus connect, heartbeat, control listener, slow-tick fallback) but
wakes on identity.> instead of attacker.> — campaign-level work is
gated on identity-layer changes, not raw observations.

The connected-components implementation reads identities via
list_identities_for_clustering, projects them with from_identity_row,
runs union-find over combined_campaign_weight, writes campaigns rows,
sets attacker_identities.campaign_id, and runs the same revocable-
merge pass as the identity layer (a merged-out campaign whose
identities no longer co-cluster with the winner gets revoked).

Bus: adds campaign.> family (formed / identity.assigned / merged /
unmerged) plus the cross-family identity.campaign.assigned so
existing identity-stream subscribers see the badge update without
having to subscribe to campaign.>. Wiki Service-Bus.md updated in
wiki-checkout in the same wave per the project's bus-signals
discipline.

CLI: decnet campaign-clusterer registered as master-only via
MASTER_ONLY_COMMANDS; --poll-interval / --daemon mirror the identity
clusterer command surface.
This commit is contained in:
2026-04-26 09:04:00 -04:00
parent 0946bab424
commit 6936a1426c
8 changed files with 1039 additions and 1 deletions

View File

@@ -29,7 +29,7 @@ MASTER_ONLY_COMMANDS: frozenset[str] = frozenset({
"api", "swarmctl", "deploy", "redeploy", "teardown",
"mutate", "listener", "profiler",
"services", "distros", "correlate", "archetypes", "web",
"db-reset", "init", "webhook", "clusterer",
"db-reset", "init", "webhook", "clusterer", "campaign-clusterer",
})
MASTER_ONLY_GROUPS: frozenset[str] = frozenset({"swarm", "topology", "geoip"})

View File

@@ -239,3 +239,59 @@ def register(app: typer.Typer) -> None:
asyncio.run(_run())
except KeyboardInterrupt:
console.print("\n[yellow]Identity clusterer stopped.[/]")
@app.command(name="campaign-clusterer")
def campaign_clusterer(
poll_interval_secs: float = typer.Option(
60.0, "--poll-interval", "-i",
help="Slow-tick fallback when the bus is idle or unavailable (seconds)",
),
daemon: bool = typer.Option(
False, "--daemon", "-d",
help="Detach to background as a daemon process",
),
) -> None:
"""Campaign clusterer — groups identities into operations.
Bus-woken on ``identity.>`` (any identity-layer change is
potential input); reads ``AttackerIdentity`` rows, runs
connected-components over the campaign-level similarity graph
(phase-handoff / shared-infra / temporal-overlap / cohort),
writes ``campaigns`` rows + sets ``attacker_identities.campaign_id``,
and publishes ``campaign.formed`` / ``campaign.identity.assigned``
/ ``campaign.merged`` / ``campaign.unmerged`` plus the cross-family
``identity.campaign.assigned`` so identity-side subscribers see
the badge update.
"""
import asyncio
from decnet.cli.gating import _require_master_mode
from decnet.clustering.campaign.worker import (
run_campaign_clusterer_loop,
)
from decnet.web.dependencies import repo
_require_master_mode("campaign-clusterer")
if daemon:
log.info("campaign-clusterer daemonizing poll=%s", poll_interval_secs)
_utils._daemonize()
log.info(
"campaign-clusterer command invoked poll=%s", poll_interval_secs,
)
console.print(
f"[bold cyan]Campaign clusterer starting[/] "
f"poll={poll_interval_secs}s"
)
console.print("[dim]Press Ctrl+C to stop[/]")
async def _run() -> None:
await repo.initialize()
await run_campaign_clusterer_loop(
repo, poll_interval_secs=poll_interval_secs,
)
try:
asyncio.run(_run())
except KeyboardInterrupt:
console.print("\n[yellow]Campaign clusterer stopped.[/]")