feat: M3 peer gossip protocol

Refs #1

- peers table (peer_id, addr, cursor, last_handshake)
- watch serves HTTP API: GET /v1/ping (knowledge vector),
  GET /v1/log?node=&after= (cursor-paged pull), POST /v1/obs/batch
- anti-entropy sweep (Run): ping, pull what we lack, push own obs;
  echo suppressed by node_id ownership; reconcile-on-pull
- config via KNOX_PEERS / KNOX_PEER_ADDR; knox gossip status
- db: GossipObservation wire type, PushObservations, ObservationsAfter,
  KnowledgeVector, peer upsert/list
- integration tests: bidirectional convergence + idempotency
This commit is contained in:
2026-08-29 04:53:26 -07:00
parent aa0dec68c1
commit 8c054094a1
10 changed files with 755 additions and 20 deletions
+114
View File
@@ -0,0 +1,114 @@
package watch
import (
"net/http/httptest"
"path/filepath"
"testing"
"github.com/david/knox/internal/db"
)
func tmpKnoxDB(t *testing.T) *db.KnoxDB {
t.Helper()
kdb, err := db.Open(filepath.Join(t.TempDir(), "index.db"))
if err != nil {
t.Fatalf("open db: %v", err)
}
t.Cleanup(func() { kdb.Close() })
return kdb
}
func seedObs(k *db.KnoxDB, prefix string) {
// Insert distinct observations only via RecordObservation so they get this
// node's node_id and HCL.
for i := 0; i < 3; i++ {
_, _, err := k.RecordObservation(db.ObservationRecord{
Fingerprint: prefix + ":" + string(rune('a'+i)),
SourceID: "test",
SourcePath: prefix,
Project: "itest",
ContentType: "test",
Title: prefix + string(rune('a'+i)),
Summary: "summary " + prefix + string(rune('a'+i)),
CreatedAt: "2026-08-29T00:00:00Z",
LineEnd: 0,
Confidence: 0.9,
IngesterVersion: "itest/v1",
})
if err != nil {
panic(err)
}
}
}
// TestGossipConvergence starts two nodes, seeds disjoint observations, and runs
// a bidirectional handshake. Both must end with the concatenation of both logs.
func TestGossipConvergence(t *testing.T) {
a := tmpKnoxDB(t)
b := tmpKnoxDB(t)
seedObs(a, "AAA")
seedObs(b, "BBB")
// Wire a and b as peer HTTP servers.
nodeA := &Node{Kdb: a, Name: "A"}
sa := httptest.NewServer(nodeA.Handler())
defer sa.Close()
nodeB := &Node{Kdb: b, Name: "B"}
sb := httptest.NewServer(nodeB.Handler())
defer sb.Close()
// A pulls from B, then B pulls from A (bidirectional sweep).
Run(a, []string{sb.URL})
Run(b, []string{sa.URL})
av, err := a.KnowledgeVector()
if err != nil {
t.Fatalf("a vector: %v", err)
}
bv, err := b.KnowledgeVector()
if err != nil {
t.Fatalf("b vector: %v", err)
}
if len(av) != 2 || len(bv) != 2 {
t.Fatalf("expected both nodes to hold 2 source logs, got a=%v b=%v", av, bv)
}
// Same maximum HCL per origin node on both sides.
for nid, hcl := range av {
if bv[nid] != hcl {
t.Errorf("node %s max hcl mismatch: a=%d b=%d", nid, hcl, bv[nid])
}
}
}
// TestGossipIdempotent ensures a repeated sweep does not duplicate observations.
func TestGossipIdempotent(t *testing.T) {
a := tmpKnoxDB(t)
b := tmpKnoxDB(t)
seedObs(a, "AAA")
nodeA := &Node{Kdb: a, Name: "A"}
sa := httptest.NewServer(nodeA.Handler())
defer sa.Close()
nodeB := &Node{Kdb: b, Name: "B"}
sb := httptest.NewServer(nodeB.Handler())
defer sb.Close()
Run(b, []string{sa.URL})
before, err := b.EntryCount()
if err != nil {
t.Fatal(err)
}
Run(b, []string{sa.URL})
after, err := b.EntryCount()
if err != nil {
t.Fatal(err)
}
if before != after {
t.Errorf("second sweep changed entry count: %d -> %d", before, after)
}
}