Files
Algis DumbrisandClaude Opus 4.7 069a985af5 feat(020): 14d window + token-budget circuit breaker + dream-agent + dashboard
Backend (Go, in this commit):
- migration 029_memory_dream_usage: per (date, owner) counters for
  tokens_in/out, jobs_started/succeeded/failed/circuit_broken
- DreamUsageStore + UsageGate (internal/messaging/dream_usage.go).
  Gate inspects today's usage against new env knobs:
  - SYNAPBUS_DREAM_RECENT_WINDOW (default 336h / 14d)
  - SYNAPBUS_DREAM_DAILY_TOKEN_LIMIT_IN (default 1M)
  - SYNAPBUS_DREAM_DAILY_TOKEN_LIMIT_OUT (default 200k)
  - SYNAPBUS_DREAM_DAILY_JOB_LIMIT (default 100)
- Consolidator now bounds watermarks + core_rewrite eligibility by the
  recency window. core_rewrite skipped for owners with no in-window
  activity. ForceRun honors the breaker.
- Recency fallback in BuildContextPacket + memory_list_unprocessed now
  accept RecentWindowDays so injection and dream queries see the same
  14d slice.
- Prometheus metrics registered (internal/metrics/metrics.go):
  synapbus_dream_jobs_total{owner,job_type,status},
  synapbus_dream_tokens_total{owner,direction},
  synapbus_dream_job_duration_seconds{owner,job_type},
  synapbus_dream_circuit_broken_total{owner,reason},
  synapbus_injection_packets_total{tool},
  synapbus_injection_memories_per_packet{tool},
  synapbus_injection_packet_chars{tool},
  synapbus_injection_skipped_total{tool,reason}.
- deploy/kubic/deployment.yaml: liveness/readiness timeoutSeconds: 1→5
  (root-causes the "connection refused" mcpproxy errors at 13:02 today —
  /readyz occasionally exceeded 1s under dream-worker tick load, so the
  pod fell out of the Service endpoints intermittently).

Dream-claude agent (Python, in /dream-agent/):
- dream_runner.py uses claude-agent-sdk 0.1.48 to drive Claude Code
  against SynapBus's MCP server. MCP transport carries
  Authorization: Bearer <api_key> AND X-Synapbus-Dispatch-Token from env
  via the SDK's McpHttpServerConfig.headers field — confirmed supported.
- Tools restricted via allowed_tools to mcp__synapbus__memory_*.
- Final JSON envelope reports tokens_in/out so harness.Usage stays
  populated and the circuit breaker can count consumption.
- Dockerfile builds linux/amd64 at 189 MB, mirroring searcher's
  agents/universal recipe.
- k8s-job-template.yaml: backoffLimit 0, ttl 600s, 512Mi/1CPU,
  Anthropic credentials via secret-ref.

Grafana dashboard (deploy/kubic/grafana/):
- dream-dashboard.json — 14 panels across 5 rows (dream activity,
  token usage vs limit, circuit breaker, injection layer, MCP
  transport health), all templated to ${DS_PROMETHEUS}.
- import.sh: resolves the cluster's Prometheus DS uid and POSTs the
  dashboard via Grafana API.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 13:58:28 +03:00

147 lines
4.1 KiB
Go

package messaging
import (
"context"
"testing"
"time"
)
func TestDreamUsageStore_RecordAndQuery(t *testing.T) {
db := newTestDB(t)
store := NewDreamUsageStore(db)
ctx := context.Background()
owner := "42"
// Start two jobs, complete one succeeded with tokens, one failed.
if err := store.RecordStart(ctx, owner); err != nil {
t.Fatalf("RecordStart: %v", err)
}
if err := store.RecordStart(ctx, owner); err != nil {
t.Fatalf("RecordStart: %v", err)
}
if err := store.RecordCompletion(ctx, owner, 1500, 700, JobStatusSucceeded); err != nil {
t.Fatalf("RecordCompletion succeeded: %v", err)
}
if err := store.RecordCompletion(ctx, owner, 0, 0, JobStatusFailed); err != nil {
t.Fatalf("RecordCompletion failed: %v", err)
}
u, err := store.Today(ctx, owner)
if err != nil {
t.Fatalf("Today: %v", err)
}
if u.JobsStarted != 2 || u.JobsSucceeded != 1 || u.JobsFailed != 1 {
t.Errorf("counters mismatch: %+v", u)
}
if u.TokensIn != 1500 || u.TokensOut != 700 {
t.Errorf("tokens mismatch: in=%d out=%d", u.TokensIn, u.TokensOut)
}
}
func TestDreamUsageStore_CircuitBrokenAccounting(t *testing.T) {
db := newTestDB(t)
store := NewDreamUsageStore(db)
ctx := context.Background()
owner := "99"
if err := store.RecordCompletion(ctx, owner, 0, 0, JobStatusCircuitBroken); err != nil {
t.Fatalf("RecordCompletion: %v", err)
}
u, _ := store.Today(ctx, owner)
if u.JobsCircuitBroken != 1 {
t.Errorf("expected jobs_circuit_broken=1, got %d", u.JobsCircuitBroken)
}
}
func TestUsageGate_AllowDeny(t *testing.T) {
db := newTestDB(t)
store := NewDreamUsageStore(db)
ctx := context.Background()
owner := "7"
cfg := DefaultMemoryConfig()
cfg.DreamDailyTokenLimitIn = 1000
cfg.DreamDailyTokenLimitOut = 500
cfg.DreamDailyJobLimit = 3
gate := NewUsageGate(cfg, store)
// Initially allowed.
allowed, reason, err := gate.Allow(ctx, owner)
if err != nil || !allowed || reason != "" {
t.Fatalf("expected initial allow, got allowed=%v reason=%q err=%v", allowed, reason, err)
}
// Push tokens_in just below the limit — still allowed.
if err := store.RecordCompletion(ctx, owner, 999, 0, JobStatusSucceeded); err != nil {
t.Fatalf("RecordCompletion: %v", err)
}
allowed, reason, _ = gate.Allow(ctx, owner)
if !allowed {
t.Errorf("expected allow at 999/1000 in, got %q", reason)
}
// Cross the input threshold — denied.
if err := store.RecordCompletion(ctx, owner, 2, 0, JobStatusSucceeded); err != nil {
t.Fatalf("RecordCompletion: %v", err)
}
allowed, reason, _ = gate.Allow(ctx, owner)
if allowed || reason != "tokens_in_exceeded" {
t.Errorf("expected tokens_in_exceeded, got allowed=%v reason=%q", allowed, reason)
}
}
func TestUsageGate_JobsExceeded(t *testing.T) {
db := newTestDB(t)
store := NewDreamUsageStore(db)
ctx := context.Background()
owner := "5"
cfg := DefaultMemoryConfig()
cfg.DreamDailyTokenLimitIn = 0 // disable token gates
cfg.DreamDailyTokenLimitOut = 0
cfg.DreamDailyJobLimit = 2
gate := NewUsageGate(cfg, store)
for i := 0; i < 2; i++ {
_ = store.RecordStart(ctx, owner)
}
allowed, reason, _ := gate.Allow(ctx, owner)
if allowed || reason != "jobs_exceeded" {
t.Errorf("expected jobs_exceeded, got allowed=%v reason=%q", allowed, reason)
}
}
func TestUsageGate_NilStoreAllows(t *testing.T) {
gate := NewUsageGate(DefaultMemoryConfig(), nil)
allowed, reason, err := gate.Allow(context.Background(), "1")
if !allowed || reason != "" || err != nil {
t.Errorf("nil store: expected allow, got %v %q %v", allowed, reason, err)
}
}
func TestDreamUsageStore_Cleanup(t *testing.T) {
db := newTestDB(t)
store := NewDreamUsageStore(db)
ctx := context.Background()
// Insert an "old" row by overriding the clock.
store.now = func() time.Time { return time.Now().AddDate(0, 0, -40).UTC() }
if err := store.RecordStart(ctx, "1"); err != nil {
t.Fatalf("RecordStart: %v", err)
}
// Restore now.
store.now = time.Now
if err := store.RecordStart(ctx, "1"); err != nil {
t.Fatalf("RecordStart: %v", err)
}
n, err := store.Cleanup(ctx, 30)
if err != nil {
t.Fatalf("Cleanup: %v", err)
}
if n != 1 {
t.Errorf("expected 1 row deleted, got %d", n)
}
}