mirror of
https://github.com/multica-ai/multica.git
synced 2026-06-17 03:38:32 +02:00
b92c3fbc93
* chore(analytics): stop shipping operational events to PostHog (MUL-2967) Operational / execution-lifecycle telemetry dominated PostHog event volume and drove the bill: runtime_offline alone was ~54% of ~22.6M events/mo, and ~99% of events were billed at the higher identified-event rate. These signals already have Prometheus counters (Grafana), so the PostHog copies were redundant cost. - Add analytics.IsMetricsOnly; metrics.RecordEvent now skips the PostHog Capture for runtime_* and autopilot_run_* while still incrementing their Prometheus counter (their analytics.Event constructors are retained to feed the metric label set via IncForEvent). - Remove the agent_task_* PostHog path entirely: drop captureTaskEvent and the AgentTask* constructors/constants. Their Prometheus side is unchanged via the typed BusinessMetrics.RecordTask* methods. Also remove the now-dead taskDurationMS / willRetryTask helpers. - Update the pairing lint test (no agent_task allow-list, no naked-Capture exception), add a RecordEvent skip test + IsMetricsOnly test, and update docs/analytics.md (taxonomy, per-event banners, reconciliation). Product/funnel events (signup, onboarding, issue_created, issue_executed, chat_message_sent, agent_created, autopilot_created, etc.) are unchanged and still ship to PostHog. Co-authored-by: multica-agent <github@multica.ai> * docs(analytics): correct agent_task Prometheus metric contract (MUL-2967) Address PR review: the agent_task_* "Prometheus-only" banner claimed the old PostHog event properties (task_id, agent_id, duration_ms, error_type, will_retry, ...) were the metric label set. They are not — the real labels are only source/runtime_mode/provider/terminal_status/failure_reason. - Replace the agent_task_* sections with the actual metric names and labels (multica_agent_task_*; see business.go / labels.go), and explain that completed/failed/cancelled are terminal_status values on multica_agent_task_terminal_total, with wall-clock in the *_seconds histograms. - Tighten the runtime_*/autopilot_run_* banners so id properties aren't mistaken for labels. - Drop the stale AgentTask allow-list reference from the pairing lint test header comment. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai>
48 lines
1.8 KiB
Go
48 lines
1.8 KiB
Go
package analytics
|
|
|
|
import "testing"
|
|
|
|
func TestRuntimeReadyOmitsUnmeasuredDuration(t *testing.T) {
|
|
ev := RuntimeReady("user-1", "workspace-1", "runtime-1", "daemon-1", "codex", 0)
|
|
if _, ok := ev.Properties["ready_duration_ms"]; ok {
|
|
t.Fatalf("ready_duration_ms should be omitted until it is measured")
|
|
}
|
|
|
|
ev = RuntimeReady("user-1", "workspace-1", "runtime-1", "daemon-1", "codex", 123)
|
|
if got := ev.Properties["ready_duration_ms"]; got != int64(123) {
|
|
t.Fatalf("ready_duration_ms = %v, want 123", got)
|
|
}
|
|
}
|
|
|
|
func TestFailedEventsUseWillRetry(t *testing.T) {
|
|
runEv := AutopilotRunFailed("user-1", "workspace-1", "autopilot-1", "run-1", "manual", AutopilotAssignee{AgentID: "agent-1", AssigneeType: "agent"}, "manual", "task failed", "task_error", false, 10)
|
|
if got := runEv.Properties["will_retry"]; got != false {
|
|
t.Fatalf("autopilot will_retry = %v, want false", got)
|
|
}
|
|
if _, ok := runEv.Properties["recoverable"]; ok {
|
|
t.Fatalf("autopilot failure should not emit recoverable")
|
|
}
|
|
}
|
|
|
|
func TestIsMetricsOnly(t *testing.T) {
|
|
// Operational / execution-lifecycle events are Prometheus-only and must
|
|
// not be shipped to PostHog.
|
|
for _, name := range []string{
|
|
EventRuntimeRegistered, EventRuntimeReady, EventRuntimeFailed, EventRuntimeOffline,
|
|
EventAutopilotRunStarted, EventAutopilotRunCompleted, EventAutopilotRunFailed,
|
|
} {
|
|
if !IsMetricsOnly(name) {
|
|
t.Errorf("IsMetricsOnly(%q) = false, want true (operational event must stay out of PostHog)", name)
|
|
}
|
|
}
|
|
// Product-behaviour events must still reach PostHog.
|
|
for _, name := range []string{
|
|
EventSignup, EventWorkspaceCreated, EventIssueCreated, EventIssueExecuted,
|
|
EventChatMessageSent, EventAgentCreated, EventAutopilotCreated,
|
|
} {
|
|
if IsMetricsOnly(name) {
|
|
t.Errorf("IsMetricsOnly(%q) = true, want false (product event must reach PostHog)", name)
|
|
}
|
|
}
|
|
}
|