Run Engine 2: More robust attempt failing/retrying (inc. OOM retrying)

.zed/tasks.json

@@ -0,0 +1,45 @@
+[
+  {
+    "label": "Build packages",
+    "command": "pnpm run build --filter \"@trigger.dev/*\" --filter trigger.dev",
+    //"args": [],
+    // Env overrides for the command, will be appended to the terminal's environment from the settings.
+    "env": { "foo": "bar" },
+    // Current working directory to spawn the command into, defaults to current project root.
+    //"cwd": "/path/to/working/directory",
+    // Whether to use a new terminal tab or reuse the existing one to spawn the process, defaults to `false`.
+    "use_new_terminal": false,
+    // Whether to allow multiple instances of the same task to be run, or rather wait for the existing ones to finish, defaults to `false`.
+    "allow_concurrent_runs": false,
+    // What to do with the terminal pane and tab, after the command was started:
+    // * `always` — always show the task's pane, and focus the corresponding tab in it (default)
+    // * `no_focus` — always show the task's pane, add the task's tab in it, but don't focus it
+    // * `never` — do not alter focus, but still add/reuse the task's tab in its pane
+    "reveal": "always",
+    // What to do with the terminal pane and tab, after the command has finished:
+    // * `never` — Do nothing when the command finishes (default)
+    // * `always` — always hide the terminal tab, hide the pane also if it was the last tab in it
+    // * `on_success` — hide the terminal tab on task success only, otherwise behaves similar to `always`
+    "hide": "never",
+    // Which shell to use when running a task inside the terminal.
+    // May take 3 values:
+    // 1. (default) Use the system's default terminal configuration in /etc/passwd
+    //      "shell": "system"
+    // 2. A program:
+    //      "shell": {
+    //        "program": "sh"
+    //      }
+    // 3. A program with arguments:
+    //     "shell": {
+    //         "with_arguments": {
+    //           "program": "/bin/bash",
+    //           "args": ["--login"]
+    //         }
+    //     }
+    "shell": "system",
+    // Whether to show the task line in the output of the spawned task, defaults to `true`.
+    "show_summary": true,
+    // Whether to show the command line in the output of the spawned task, defaults to `true`.
+    "show_output": true
+  }
+]

apps/docker-provider/src/index.ts

@@ -8,7 +8,7 @@ import {
 } from "@trigger.dev/core/v3/apps";
 import { SimpleLogger } from "@trigger.dev/core/v3/apps";
 import { isExecaChildProcess } from "@trigger.dev/core/v3/apps";
-import { testDockerCheckpoint } from "@trigger.dev/core/v3/checkpoints";
+import { testDockerCheckpoint } from "@trigger.dev/core/v3/serverOnly";
 import { setTimeout } from "node:timers/promises";
 import { PostStartCauses, PreStopCauses } from "@trigger.dev/core/v3";
 

apps/webapp/app/v3/services/alerts/deliverAlert.server.ts

@@ -13,6 +13,7 @@ import {
   RunFailedWebhook,
   DeploymentFailedWebhook,
   DeploymentSuccessWebhook,
+  isOOMRunError,
 } from "@trigger.dev/core/v3";
 import assertNever from "assert-never";
 import { subtle } from "crypto";
@@ -39,7 +40,6 @@ import { generateFriendlyId } from "~/v3/friendlyIdentifiers";
 import { ProjectAlertChannelType, ProjectAlertType } from "@trigger.dev/database";
 import { alertsRateLimiter } from "~/v3/alertsRateLimiter.server";
 import { v3RunPath } from "~/utils/pathBuilder";
-import { isOOMError } from "../completeAttempt.server";
 import { ApiRetrieveRunPresenter } from "~/presenters/v3/ApiRetrieveRunPresenter.server";
 
 type FoundAlert = Prisma.Result<
@@ -375,7 +375,7 @@ export class DeliverAlertService extends BaseService {
                     idempotencyKey: alert.taskRun.idempotencyKey ?? undefined,
                     tags: alert.taskRun.runTags,
                     error,
-                    isOutOfMemoryError: isOOMError(error),
+                    isOutOfMemoryError: isOOMRunError(error),
                     machine: alert.taskRun.machinePreset ?? "Unknown",
                     dashboardUrl: `${env.APP_ORIGIN}${v3RunPath(
                       alert.project.organization,

apps/webapp/app/v3/services/completeAttempt.server.ts

@@ -11,6 +11,7 @@ import {
   TaskRunSuccessfulExecutionResult,
   flattenAttributes,
   isManualOutOfMemoryError,
+  isOOMRunError,
   sanitizeError,
   shouldRetryError,
   taskRunErrorEnhancer,
@@ -255,7 +256,7 @@ export class CompleteAttemptService extends BaseService {
 
     let retriableError = shouldRetryError(taskRunErrorEnhancer(completion.error));
     let isOOMRetry = false;
-    let isOOMAttempt = isOOMError(completion.error);
+    let isOOMAttempt = isOOMRunError(completion.error);
     let isOnMaxOOMMachine = false;
     let oomMachine: MachinePresetName | undefined;
 
@@ -738,45 +739,6 @@ async function findAttempt(prismaClient: PrismaClientOrTransaction, friendlyId:
   });
 }
 
-export function isOOMError(error: TaskRunError) {
-  if (error.type === "INTERNAL_ERROR") {
-    if (
-      error.code === "TASK_PROCESS_OOM_KILLED" ||
-      error.code === "TASK_PROCESS_MAYBE_OOM_KILLED"
-    ) {
-      return true;
-    }
-
-    // For the purposes of retrying on a larger machine, we're going to treat this is an OOM error.
-    // This is what they look like if we're executing using k8s. They then get corrected later, but it's too late.
-    // {"code": "TASK_PROCESS_EXITED_WITH_NON_ZERO_CODE", "type": "INTERNAL_ERROR", "message": "Process exited with code -1 after signal SIGKILL."}
-    if (
-      error.code === "TASK_PROCESS_EXITED_WITH_NON_ZERO_CODE" &&
-      error.message &&
-      error.message.includes("SIGKILL") &&
-      error.message.includes("-1")
-    ) {
-      return true;
-    }
-  }
-
-  if (error.type === "BUILT_IN_ERROR") {
-    // ffmpeg also does weird stuff
-    // { "name": "Error", "type": "BUILT_IN_ERROR", "message": "ffmpeg was killed with signal SIGKILL" }
-    if (error.message && error.message.includes("ffmpeg was killed with signal SIGKILL")) {
-      return true;
-    }
-  }
-
-  // Special `OutOfMemoryError` for doing a manual OOM kill.
-  // Useful if a native library does an OOM but doesn't actually crash the run and you want to manually
-  if (isManualOutOfMemoryError(error)) {
-    return true;
-  }
-
-  return false;
-}
-
 function exitRun(runId: string) {
   socketIo.coordinatorNamespace.emit("REQUEST_RUN_CANCELLATION", {
     version: "v1",