Merge pull request #444 from ArnasDon/fix/409-automation-dispatch-reliability

fix(automations): stop inbound runs being dropped and mislogged

src/app/api/whatsapp/webhook/route.ts

@@ -781,8 +781,16 @@ async function processMessage(
   // listens to only one trigger runs only when that trigger matches.
   if (contactOutcome.wasCreated) automationTriggers.unshift('new_contact_created')
   if (isFirstInboundMessage) automationTriggers.unshift('first_inbound_message')
+  // Awaited — not fire-and-forget. We're inside the route's `after()`
+  // block, which only keeps the function alive for promises it can see, so
+  // a detached dispatch can be frozen part-way through: the log row is
+  // inserted, then the steps never run. That is issue #301's failure mode
+  // recurring one level down, and it's what issue #409 reported as runs
+  // logging zero steps. `runAutomationsForTrigger` owns its own try/catch
+  // and never throws; the `.catch` is belt-and-braces so one trigger
+  // type's failure can't skip the rest of the loop.
   for (const triggerType of automationTriggers) {
-    runAutomationsForTrigger({
+    await runAutomationsForTrigger({
       accountId,
       triggerType,
       contactId: contactRecord.id,

src/lib/automations/engine.test.ts

@@ -11,6 +11,7 @@ const h = vi.hoisted(() => ({
     fromCalls: [] as string[],
     updateCalls: [] as { table: string; filters: [string, string, unknown][] }[],
     upsertCalls: [] as { table: string; payload: unknown }[],
+    logInserts: [] as Record<string, unknown>[],
     logUpdates: [] as Record<string, unknown>[],
   },
 }));
@@ -46,7 +47,10 @@ vi.mock("./admin-client", () => {
     }
     if (table === "automations") return { data: state.automations, error: null };
     if (table === "automation_logs") {
-      if (type === "insert") return { data: { id: "log1" }, error: null };
+      if (type === "insert") {
+        state.logInserts.push(ops.payload as Record<string, unknown>);
+        return { data: { id: "log1" }, error: null };
+      }
       if (type === "update") {
         state.logUpdates.push(ops.payload as Record<string, unknown>);
         return { data: null, error: null };
@@ -113,6 +117,7 @@ beforeEach(() => {
   h.state.fromCalls = [];
   h.state.updateCalls = [];
   h.state.upsertCalls = [];
+  h.state.logInserts = [];
   h.state.logUpdates = [];
 });
 
@@ -170,6 +175,47 @@ describe("runAutomationsForTrigger — tenant isolation", () => {
   });
 });
 
+describe("automation_logs — status is seeded pessimistically (issue #409)", () => {
+  it("writes the log row as 'failed' before any step runs", async () => {
+    h.state.owned = { id: "c1" };
+    h.state.automations = [automationWithUpdateStep()];
+    h.state.steps = [updateStep()];
+
+    await runAutomationsForTrigger({
+      accountId: ACCOUNT,
+      triggerType: "new_message_received",
+      contactId: "c1",
+      context: {},
+    });
+
+    // The insert happens before execution, so a run killed mid-flight must
+    // not leave behind a row that claims it succeeded.
+    expect(h.state.logInserts).toHaveLength(1);
+    expect(h.state.logInserts[0]).toMatchObject({
+      status: "failed",
+      steps_executed: [],
+    });
+  });
+
+  it("still promotes the log to 'success' once the steps complete", async () => {
+    h.state.owned = { id: "c1" };
+    h.state.automations = [automationWithUpdateStep()];
+    h.state.steps = [updateStep()];
+
+    await runAutomationsForTrigger({
+      accountId: ACCOUNT,
+      triggerType: "new_message_received",
+      contactId: "c1",
+      context: {},
+    });
+
+    // The seed is only a floor — the outermost scope still writes the real
+    // verdict, so a completed run reports success as it always did.
+    const withStatus = h.state.logUpdates.filter((u) => "status" in u);
+    expect(withStatus.at(-1)).toMatchObject({ status: "success" });
+  });
+});
+
 describe("update_contact_field — custom fields", () => {
   it("upserts contact_custom_values when the field is account-owned", async () => {
     h.state.owned = { id: "c1" };

src/lib/automations/engine.ts

@@ -189,7 +189,15 @@ async function executeAutomation(automation: Automation, input: DispatchInput) {
       contact_id: input.contactId ?? null,
       trigger_event: input.triggerType,
       steps_executed: [],
-      status: 'success',
+      // Seeded pessimistically. The row is written BEFORE any step runs,
+      // and every terminal path below overwrites it (`appendResults` at
+      // the outermost scope, or `finalizeLog`). Seeding 'success' meant a
+      // run that died mid-flight — the process frozen, the pod recycled —
+      // left a permanent `status: 'success'` with `steps_executed: []`,
+      // indistinguishable from an automation that genuinely had nothing
+      // to do. 'failed' inverts that: the status only becomes success if
+      // execution actually reached the end. See issue #409.
+      status: 'failed',
     })
     .select()
     .single()