Release 3.0.0-beta.36

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.changeset/afraid-sheep-joke.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fixes an issue with scoped packages in additionalPackages option

.changeset/angry-eagles-trade.md

@@ -0,0 +1,9 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+- Fix additionalFiles that aren't decendants
+- Stop swallowing uncaught exceptions in prod
+- Improve warnings and errors, fail early on critical warnings
+- New arg to --save-logs even for successful builds

.changeset/beige-pens-dance.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+v3 CLI update command and package manager detection fix

.changeset/big-tomatoes-deliver.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Hoist uncaughtException handler to the top of workers to better report error messages

.changeset/blue-pumas-whisper.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/shopify": patch
+---
+
+improved error messages when a shopify webhook fails to register

.changeset/clever-apes-collect.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Fix error stack traces

.changeset/clever-carrots-travel.md

@@ -0,0 +1,7 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Implement task.onSuccess/onFailure and config.onSuccess/onFailure

.changeset/clever-donkeys-hunt.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Remove "log" Log Level, unify log and info messages under the "info" log level

.changeset/config.json

@@ -4,7 +4,8 @@
   "commit": false,
   "fixed": [
     [
-      "@trigger.dev/*"
+      "@trigger.dev/*",
+      "trigger.dev"
     ]
   ],
   "linked": [],

.changeset/cool-comics-burn.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fixing missing logs when importing client @opentelemetry/api

.changeset/cuddly-feet-approve.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Don’t swallow some error messages when deploying

.changeset/dry-walls-check.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Add option to print console logs in the dev CLI locally (issue #1014)

.changeset/dull-mangos-press.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Strip out server-only package from worker builds

.changeset/eleven-paws-join.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Remove the env var check during deploy (too many false negatives)

.changeset/famous-boats-tease.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Better handle issues with resolving dependency versions during deploy

.changeset/five-toes-destroy.md

@@ -0,0 +1,7 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+v3: Environment variable management API and SDK, along with resolveEnvVars CLI hook

.changeset/funny-swans-destroy.md

@@ -0,0 +1,9 @@
+---
+"@trigger.dev/sdk": patch
+---
+
+Make msw a normal dependency (for now) to fix Module Not Found error in Next.js.
+
+It turns out that webpack will "hoist" dynamically imported modules and attempt to resolve them at build time, even though it's an optional peer dep:
+
+https://x.com/maverickdotdev/status/1782465214308319404

.changeset/gorgeous-gorillas-compete.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Add runs.retrieve management API method to get info about a run by run ID

.changeset/hot-buckets-behave.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Support triggering tasks with non-URL friendly characters in the ID

.changeset/hot-fishes-retire.md

@@ -0,0 +1,5 @@
+---
+trigger.dev: patch
+---
+
+Fix TypeScript inclusion in tsconfig.json for `cli-v3 init`

.changeset/itchy-chairs-itch.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/sdk": patch
+---
+
+Fix for calling trigger and passing a custom queue

.changeset/khaki-poems-lay.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/sdk": patch
+---
+
+Export queue from the SDK

.changeset/late-steaks-behave.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+v3: fix digest extraction

.changeset/lazy-files-lay.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Increased the timeout when canceling a checkpoint to 31s (to match the timeout on the server)

.changeset/little-crabs-cross.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Fix issues with consecutive waits

.changeset/long-fireants-search.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Adding some additional telemetry during deploy to help debug issues

.changeset/lovely-drinks-flash.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Add the "log" level back in as an alias to "info"

.changeset/mighty-flowers-train.md

@@ -0,0 +1,83 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Adds support for `emitDecoratorMetadata: true` and `experimentalDecorators: true` in your tsconfig using the [`@anatine/esbuild-decorators`](https://github.com/anatine/esbuildnx/tree/main/packages/esbuild-decorators) package. This allows you to use libraries like TypeORM: 
+
+```ts orm/index.ts
+import "reflect-metadata";
+import { DataSource } from "typeorm";
+import { Entity, Column, PrimaryColumn } from "typeorm";
+
+@Entity()
+export class Photo {
+  @PrimaryColumn()
+  id!: number;
+
+  @Column()
+  name!: string;
+
+  @Column()
+  description!: string;
+
+  @Column()
+  filename!: string;
+
+  @Column()
+  views!: number;
+
+  @Column()
+  isPublished!: boolean;
+}
+
+export const AppDataSource = new DataSource({
+  type: "postgres",
+  host: "localhost",
+  port: 5432,
+  username: "postgres",
+  password: "postgres",
+  database: "v3-catalog",
+  entities: [Photo],
+  synchronize: true,
+  logging: false,
+});
+```
+
+And then in your trigger.config.ts file you can initialize the datasource using the new `init` option:
+
+```ts trigger.config.ts
+import type { TriggerConfig } from "@trigger.dev/sdk/v3";
+import { AppDataSource } from "@/trigger/orm";
+
+export const config: TriggerConfig = {
+  // ... other options here
+  init: async (payload, { ctx }) => {
+    await AppDataSource.initialize();
+  },
+};
+```
+
+Now you are ready to use this in your tasks:
+
+```ts
+import { task } from "@trigger.dev/sdk/v3";
+import { AppDataSource, Photo } from "./orm";
+
+export const taskThatUsesDecorators = task({
+  id: "taskThatUsesDecorators",
+  run: async (payload: { message: string }) => {
+    console.log("Creating a photo...");
+
+    const photo = new Photo();
+    photo.id = 2;
+    photo.name = "Me and Bears";
+    photo.description = "I am near polar bears";
+    photo.filename = "photo-with-bears.jpg";
+    photo.views = 1;
+    photo.isPublished = true;
+
+    await AppDataSource.manager.save(photo);
+  },
+});
+```

.changeset/nasty-jars-pump.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fixes an issue that was treating v2 trigger directories as v3

.changeset/new-pants-beg.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Fix issue when using SDK in non-node environments by scoping the stream import with node:

.changeset/new-rivers-tell.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Added replayRun function to the SDK

.changeset/nice-bulldogs-turn.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Better handle uncaught exceptions

.changeset/ninety-pets-travel.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Improve the SDK function types and expose a new APIError instead of the APIResult type

.changeset/pink-pumas-rhyme.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Add configure function to be able to configure the SDK manually

.changeset/polite-rockets-matter.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fix dev CLI output when not printing update messages

.changeset/poor-flowers-cross.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Use the dashboard url instead of the API url for the View logs link

.changeset/pre.json

@@ -44,31 +44,102 @@
     "@trigger.dev/yalt": "2.3.18"
   },
   "changesets": [
+    "afraid-sheep-joke",
+    "angry-eagles-trade",
+    "beige-pens-dance",
+    "big-tomatoes-deliver",
+    "blue-pumas-whisper",
     "breezy-gorillas-mate",
     "chilled-hornets-move",
     "clean-pianos-listen",
+    "clever-apes-collect",
+    "clever-carrots-travel",
+    "clever-donkeys-hunt",
+    "cool-comics-burn",
     "cool-glasses-bake",
+    "cuddly-feet-approve",
+    "dry-walls-check",
+    "dull-mangos-press",
     "eight-pumas-float",
+    "eleven-paws-join",
+    "famous-boats-tease",
     "few-students-share",
+    "five-toes-destroy",
+    "funny-swans-destroy",
+    "gorgeous-gorillas-compete",
     "green-bags-wink",
+    "hot-buckets-behave",
+    "hot-fishes-retire",
+    "itchy-chairs-itch",
     "khaki-apricots-design",
+    "khaki-poems-lay",
     "late-icons-lie",
+    "late-steaks-behave",
+    "lazy-files-lay",
     "lemon-jobs-repair",
     "light-bulldogs-press",
     "light-dragons-complain",
+    "little-crabs-cross",
+    "long-fireants-search",
     "loud-actors-remember",
+    "lovely-drinks-flash",
     "many-ligers-pump",
     "mighty-camels-joke",
+    "mighty-flowers-train",
+    "nasty-jars-pump",
+    "new-pants-beg",
+    "new-rivers-tell",
+    "nice-bulldogs-turn",
+    "ninety-pets-travel",
     "odd-poets-own",
+    "pink-pumas-rhyme",
     "polite-ducks-switch",
+    "polite-rockets-matter",
+    "poor-flowers-cross",
+    "purple-garlics-shop",
+    "rare-lamps-promise",
+    "rare-roses-float",
     "real-planets-stare",
+    "rich-kangaroos-unite",
+    "rotten-beers-refuse",
+    "rotten-dryers-exercise",
+    "selfish-ducks-sort",
+    "shaggy-spoons-taste",
+    "sharp-emus-compare",
     "sharp-zebras-serve",
+    "shiny-coats-cry",
+    "silly-suits-switch",
+    "six-ligers-exist",
+    "sixty-insects-watch",
+    "slow-buses-own",
+    "smart-needles-move",
     "smart-olives-eat",
     "spicy-lamps-smoke",
     "strange-ghosts-matter",
+    "strange-sheep-pull",
+    "strong-lemons-add",
+    "strong-owls-know",
+    "stupid-adults-sniff",
     "stupid-bulldogs-applaud",
     "sweet-lizards-press",
+    "swift-dragons-peel",
     "tall-bees-wave",
-    "tame-guests-know"
+    "tame-guests-know",
+    "tender-moose-tell",
+    "tender-oranges-rhyme",
+    "thin-parents-heal",
+    "thirty-islands-kiss",
+    "tidy-balloons-suffer",
+    "tidy-dryers-sleep",
+    "tidy-tomatoes-explain",
+    "tiny-doors-type",
+    "tiny-elephants-scream",
+    "tricky-bulldogs-heal",
+    "tricky-keys-attack",
+    "tricky-ladybugs-unite",
+    "two-pumas-wait",
+    "warm-olives-provide",
+    "warm-planes-taste",
+    "young-snails-sell"
   ]
 }

.changeset/purple-garlics-shop.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Add typescript as a dependency so the esbuild-decorator will work even when running in npx

.changeset/rare-lamps-promise.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Add a postInstall option to allow running scripts after dependencies have been installed in deployed images

.changeset/rare-roses-float.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Add openssl to prod worker image and allow passing auth token via env var for deploy

.changeset/rich-kangaroos-unite.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fix a bug where revoking the CLI token would prevent you from ever logging in again with the CLI.

.changeset/rotten-beers-refuse.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Add git to prod worker image which fixes private package installs

.changeset/rotten-dryers-exercise.md

@@ -0,0 +1,7 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Adding task with a triggerSource of schedule

.changeset/selfish-ducks-sort.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+---
+
+Lock SDK and CLI deps on exact core version

.changeset/shaggy-spoons-taste.md

@@ -0,0 +1,56 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Updates the `trigger`, `batchTrigger` and their `*AndWait` variants to use the first parameter for the payload/items, and the second parameter for options.
+
+Before:
+
+```ts
+await yourTask.trigger({ payload: { foo: "bar" }, options: { idempotencyKey: "key_1234" } });
+await yourTask.triggerAndWait({ payload: { foo: "bar" }, options: { idempotencyKey: "key_1234" } });
+
+await yourTask.batchTrigger({ items: [{ payload: { foo: "bar" } }, { payload: { foo: "baz" } }] });
+await yourTask.batchTriggerAndWait({ items: [{ payload: { foo: "bar" } }, { payload: { foo: "baz" } }] });
+```
+
+After:
+
+```ts
+await yourTask.trigger({ foo: "bar" }, { idempotencyKey: "key_1234" });
+await yourTask.triggerAndWait({ foo: "bar" }, { idempotencyKey: "key_1234" });
+
+await yourTask.batchTrigger([{ payload: { foo: "bar" } }, { payload: { foo: "baz" } }]);
+await yourTask.batchTriggerAndWait([{ payload: { foo: "bar" } }, { payload: { foo: "baz" } }]);
+```
+
+We've also changed the API of the `triggerAndWait` result. Before, if the subtask that was triggered finished with an error, we would automatically "rethrow" the error in the parent task.
+
+Now instead we're returning a `TaskRunResult` object that allows you to discriminate between successful and failed runs in the subtask:
+
+Before:
+
+```ts
+try {
+  const result = await yourTask.triggerAndWait({ foo: "bar" });
+
+  // result is the output of your task
+  console.log("result", result);
+
+} catch (error) {
+  // handle subtask errors here
+}
+```
+
+After:
+
+```ts
+const result = await yourTask.triggerAndWait({ foo: "bar" });
+
+if (result.ok) {
+  console.log(`Run ${result.id} succeeded with output`, result.output);
+} else {
+  console.log(`Run ${result.id} failed with error`, result.error);
+}
+```

.changeset/sharp-emus-compare.md

@@ -0,0 +1,13 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+When using idempotency keys, triggerAndWait and batchTriggerAndWait will still work even if the existing runs have already been completed (or even partially completed, in the case of batchTriggerAndWait)
+
+- TaskRunExecutionResult.id is now the run friendlyId, not the attempt friendlyId
+- A single TaskRun can now have many batchItems, in the case of batchTriggerAndWait while using idempotency keys
+- A run’s idempotencyKey is now added to the ctx as well as the TaskEvent and displayed in the span view
+- When resolving batchTriggerAndWait, the runtimes no longer reject promises, leading to an error in the parent task
+

.changeset/shiny-coats-cry.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Add additional logging around cleaning up dev workers, and always kill them after 5 seconds if they haven't already exited

.changeset/silly-suits-switch.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/otlp-importer": patch
+"trigger.dev": patch
+---
+
+Fix package builds and CLI commands on Windows

.changeset/six-ligers-exist.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Improve the display of non-object return types in the run trace viewer

.changeset/sixty-insects-watch.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Set the deploy timeout to 3mins from 1min

.changeset/slow-buses-own.md

@@ -0,0 +1,8 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+"@trigger.dev/cli": patch
+---
+
+Move to our global system from AsyncLocalStorage for the current task context storage

.changeset/smart-needles-move.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/sdk": patch
+---
+
+Remove unimplemented batchOptions

.changeset/strange-sheep-pull.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+v2: Better handle recovering from platform communication errors by auto-yielding back to the platform in case of temporary API failures

.changeset/strong-lemons-add.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Make optional schedule object fields nullish

.changeset/strong-owls-know.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+When a v2 run hits the rate limit, reschedule with the reset date

.changeset/stupid-adults-sniff.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Management SDK overhaul and adding the runs.list API

.changeset/swift-dragons-peel.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Added JSDocs to the schedule SDK types

.changeset/tender-moose-tell.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Use locked package versions when resolving dependencies in deployed workers

.changeset/tender-oranges-rhyme.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Stop swallowing deployment errors and display them better

.changeset/thin-parents-heal.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Ensure @trigger.dev/sdk and @trigger.dev/core are always in the list of deployed dependencies

.changeset/thirty-islands-kiss.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fix for typo in v3 CLI login command

.changeset/tidy-balloons-suffer.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Init command was failing on Windows because of bad template paths

.changeset/tidy-dryers-sleep.md

@@ -0,0 +1,10 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Fixes an issue that caused failed tasks when resuming after calling `triggerAndWait` or `batchTriggerAndWait` in prod/staging (this doesn't effect dev).
+
+The version of Node.js we use for deployed workers (latest 20) would crash with an out-of-memory error when the checkpoint was restored. This crash does not happen on Node 18x or Node21x, so we've decided to upgrade the worker version to Node.js21x, to mitigate this issue.
+
+You'll need to re-deploy to production to fix the issue.

.changeset/tidy-tomatoes-explain.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Fix 3rd party otel propagation from breaking our Task Events data from being properly correlated to the correct trace

.changeset/tiny-doors-type.md

@@ -0,0 +1,6 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core": patch
+---
+
+Added cancelRun to the SDK

.changeset/tiny-elephants-scream.md

@@ -0,0 +1,7 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+- Add graceful exit for prod workers
+- Prevent overflow in long waits

.changeset/tricky-bulldogs-heal.md

@@ -0,0 +1,7 @@
+---
+"@trigger.dev/sdk": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Added a new global - Task Catalog - to better handle task metadata

.changeset/tricky-keys-attack.md

@@ -0,0 +1,14 @@
+---
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+- Clear paused states before retry
+- Detect and handle unrecoverable worker errors
+- Remove checkpoints after successful push
+- Permanently switch to DO hosted busybox image
+- Fix IPC timeout issue, or at least handle it more gracefully
+- Handle checkpoint failures
+- Basic chaos monkey for checkpoint testing
+- Stack traces are back in the dashboard
+- Display final errors on root span

.changeset/tricky-ladybugs-unite.md

@@ -0,0 +1,8 @@
+---
+"@trigger.dev/sdk": patch
+"@trigger.dev/core-apps": patch
+"trigger.dev": patch
+"@trigger.dev/core": patch
+---
+
+Extracting out all the non-SDK related features from the main @trigger.dev/core/v3 export

.changeset/two-pumas-wait.md

@@ -0,0 +1,6 @@
+---
+"trigger.dev": patch
+"@trigger.dev/cli": patch
+---
+
+Add support for tasks located in subdirectories inside trigger dirs

.changeset/warm-olives-provide.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Improve handling of IPC timeouts and fix checkpoint cancellation after failures

.changeset/warm-planes-taste.md

@@ -0,0 +1,7 @@
+---
+"trigger.dev": patch
+---
+
+v3: Prevent legacy-peer-deps=true from breaking deploys
+
+When a global `.npmrc` file includes `legacy-peer-deps=true`, deploys would fail on the `npm ci` step because the package-lock.json wouldn't match the `package.json` file. This is because inside the image build, the `.npmrc` file would not be picked up and so `legacy-peer-deps` would end up being false (which is the default). This change forces the `package-lock.json` file to be created using `legacy-peer-deps=false`

.changeset/young-snails-sell.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Increase cleanup IPC timeout

.env.example

@@ -11,11 +11,16 @@ REMIX_APP_PORT=3030
 APP_ENV=development
 APP_ORIGIN=http://localhost:3030
 NODE_ENV=development
+CLOUD_ENV=development
+V3_ENABLED=true
 
-# Redis is used for concurrency control
-# REDIS_HOST="localhost"
-# REDIS_PORT="6379"
-# REDIS_TLS_DISABLED="true"
+# Redis is used for the v3 queuing and v2 concurrency control
+REDIS_HOST="localhost"
+REDIS_PORT="6379"
+REDIS_TLS_DISABLED="true"
+
+DEV_OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:3030/otel"
+DEV_OTEL_BATCH_PROCESSING_ENABLED="0"
 
 # OPTIONAL VARIABLES
 # This is used for validating emails that are allowed to log in. Every email that do not match this regex will be rejected.

.github/workflows/pr_checks.yml

@@ -27,6 +27,6 @@ jobs:
     uses: ./.github/workflows/unit-tests.yml
     secrets: inherit
 
-  e2e:
-    uses: ./.github/workflows/e2e.yml
-    secrets: inherit
+  # e2e:
+  #   uses: ./.github/workflows/e2e.yml
+  #   secrets: inherit

.github/workflows/publish-docker.yml

@@ -4,13 +4,15 @@ on:
 jobs:
   publish:
     runs-on: ubuntu-latest
+    env:
+      PRISMA_ENGINES_CHECKSUM_IGNORE_MISSING: 1
     outputs:
       version: ${{ steps.get_version.outputs.version }}
       short_sha: ${{ steps.get_commit.outputs.sha_short }}
     steps:
       - name: Setup Depot CLI
         uses: depot/setup-action@v1
-        
+
       - name: ⬇️ Checkout repo
         uses: actions/checkout@v3
         with:

.github/workflows/publish.yml

@@ -49,11 +49,11 @@ jobs:
     uses: ./.github/workflows/unit-tests.yml
     secrets: inherit
 
-  e2e:
-    uses: ./.github/workflows/e2e.yml
-    secrets: inherit
+  # e2e:
+  #   uses: ./.github/workflows/e2e.yml
+  #   secrets: inherit
 
   publish:
-    needs: [typecheck, units, e2e]
+    needs: [typecheck, units]
     uses: ./.github/workflows/publish-docker.yml
     secrets: inherit

.vscode/launch.json

@@ -23,7 +23,7 @@
     {
       "type": "node-terminal",
       "request": "launch",
-      "name": "Debug BYO Auth",
+      "name": "Debug v2 job catalog",
       "command": "pnpm run byo-auth",
       "envFile": "${workspaceFolder}/references/job-catalog/.env",
       "cwd": "${workspaceFolder}/references/job-catalog",
@@ -45,6 +45,14 @@
       "cwd": "${workspaceFolder}/references/v3-catalog",
       "sourceMaps": true
     },
+    {
+      "type": "node-terminal",
+      "request": "launch",
+      "name": "Debug V3 Management",
+      "command": "pnpm run management",
+      "cwd": "${workspaceFolder}/references/v3-catalog",
+      "sourceMaps": true
+    },
     {
       "type": "node",
       "request": "attach",

CONTRIBUTING.md

@@ -10,13 +10,14 @@ Thank you for helping us make Trigger.dev even better! 🤩
 
 The development branch is `main`. This is the branch that all pull
 requests should be made against. The changes on the `main`
-branch are tagged into a release monthly.
+branch are tagged into a release periodically.
 
 ### Prerequisites
 
-- [Node.js](https://nodejs.org/en) version >=16.x
-- [pnpm package manager](https://pnpm.io/installation) version 7
+- [Node.js](https://nodejs.org/en) version 20.11.1
+- [pnpm package manager](https://pnpm.io/installation) version 8.15.5
 - [Docker](https://www.docker.com/get-started/)
+- [protobuf](https://github.com/protocolbuffers/protobuf)
 
 ### Setup
 
@@ -33,15 +34,19 @@ branch are tagged into a release monthly.
    ```
    cd trigger.dev
    ```
-3. Install the required packages using pnpm.
+3. Ensure you are on the correct version of Node.js (20.11.1). If you are using `nvm`, there is an `.nvmrc` file that will automatically select the correct version of Node.js when you navigate to the repository.
+
+4. Run `corepack enable` to use the correct version of pnpm (`8.15.5`) as specified in the root `package.json` file.
+
+5. Install the required packages using pnpm.
    ```
    pnpm i
    ```
-4. Create your `.env` file
+6. Create your `.env` file
    ```
    cp .env.example .env
    ```
-5. Open it and generate a new value for `ENCRYPTION_KEY`:
+7. Open it and generate a new value for `ENCRYPTION_KEY`:
 
    `ENCRYPTION_KEY` is used to two-way encrypt OAuth access tokens and so you'll probably want to actually generate a unique value, and it must be a random 16 byte hex string. You can generate one with the following command:
 
@@ -51,7 +56,7 @@ branch are tagged into a release monthly.
 
    Feel free to update `SESSION_SECRET` and `MAGIC_LINK_SECRET` as well using the same method.
 
-6. Start Docker. This starts the required services like Postgres. If this is your first time using Docker, consider going through this [guide](DOCKER_INSTALLATION.md)
+8. Start Docker. This starts the required services like Postgres & Redis. If this is your first time using Docker, consider going through this [guide](DOCKER_INSTALLATION.md)
 
    ```
    pnpm run docker
@@ -59,19 +64,15 @@ branch are tagged into a release monthly.
 
    This will also start and run a local instance of [pgAdmin](https://www.pgadmin.org/) on [localhost:5480](http://localhost:5480), preconfigured with email `admin@example.com` and pwd `admin`. Then use `postgres` as the password to the Trigger.dev server.
 
-7. Migrate the database
+9. Migrate the database
    ```
    pnpm run db:migrate
    ```
-8. Build the app
-   ```
-   pnpm run build --filter webapp
-   ```
-9. Run the seed script
-   ```
-   pnpm run db:seed
-   ```
-10. Run the app. See the section below.
+10. Build the server app
+    ```
+    pnpm run build --filter webapp
+    ```
+11. Run the app. See the section below.
 
 ## Running
 
@@ -83,99 +84,96 @@ branch are tagged into a release monthly.
 
    It should run on port `3030`: [http://localhost:3030](http://localhost:3030/)
 
-2. Once the app is running click the magic link button and enter your email.
-3. Check your terminal, the magic link email should have printed out as following:
+2. Once the app is running click the magic link button and enter your email. You will automatically be logged in, since you are running locally. Create an Org and your first project in the dashboard.
 
-   ```sh
-   webapp:dev: Log in to Trigger.dev
-   webapp:dev:
-   webapp:dev: Click here to log in with this magic link
-   webapp:dev: [http://localhost:3030/magic?token=U2FsdGVkX18OvB0JxgaswTLCSbaRz%2FY82TN0EZWhSzFyZYwgG%2BIzKVTkeiaOtWfotPw7F8RwFzCHh53aBpMEu%2B%2B%2FItb%2FcJYh89MSjc3Pz92bevoEjqxSQ%2Ff%2BZbks09JOpqlBbYC3FzGWC8vuSVFBlxqLXxteSDLthZSUaC%2BS2LaA%2BJgp%2BLO7hgjAaC2lXbCHrM7MTgTdXOFt7i0Dvvuwz6%2BWY25RnfomZOPqDsyH0xz8Q2rzPTz0Xu53WSXrZ1hd]
-   webapp:dev:
-   webapp:dev: If you didn't try to log in, you can safely ignore this email.
-   ```
+## Manual testing using v3-catalog
 
-   Paste the magic link shown in your terminal into your browser to login.
+We use the `<root>/references/v3-catalog` subdirectory as a staging ground for testing changes to the SDK (`@trigger.dev/sdk` at `<root>/packages/trigger-sdk`), the Core package (`@trigger.dev/core` at `<root>packages/core`), the CLI (`trigger.dev` at `<root>/packages/cli-v3`) and the platform (The remix app at `<root>/apps/webapp`). The instructions below will get you started on using the `v3-catalog` for local development of Trigger.dev (v3).
 
-## Adding and running migrations
+### First-time setup
 
-1. Modify packages/database/prisma/schema.prisma file
-2. Change directory to the packages/database folder
-   ```sh
-   cd packages/database
-   ```
-3. Generate the Prisma client
+First, make sure you are running the webapp according to the instructions above. Then:
 
-   ```sh
-   pnpm run generate
-   ```
+1. In Postgres go to the "Organizations" table and on your org set the `v3Enabled` column to `true`.
 
-   The above updates the prisma client generated into node_modules/.prisma/client folder. This helps with typing of relevant prisma models. It ensures typescript
-   recognizes fields added or removed from a model and type-checks appropriately.
+2. Visit http://localhost:3030 in your browser and create a new V3 project called "v3-catalog". If you don't see an option for V3, you haven't set the `v3Enabled` flag to true.
 
-4. Create and apply the migrations
+3. In Postgres go to the "Projects" table and for the project you create change the `externalRef` to `yubjwjsfkxnylobaqvqz`.
 
-   ```
-   pnpm run db:migrate:dev
-   ```
-
-   This creates a migration file and executes the migrations against your database and applies changes to the database schema(s)
-
-5. Commit generated migrations as well as changes to the schema.prisma file
-6. If you're using VSCode you may need to restart the Typescript server in the webapp to get updated type inference. Open a TypeScript file, then open the Command Palette (View > Command Palette) and run `TypeScript: Restart TS server`.
-
-## Testing CLI changes
-
-To test CLI changes, follow the steps below:
-
-1. Build the CLI and watch for changes
+4. Build the CLI
 
 ```sh
-cd packages/cli
-pnpm run dev
-```
-
-2. Open a new Terminal window and run the webapp locally and then create a new project in the dashboard. Copy out the dev API key.
-
-3. Create a new temporary Next.js app in references directory
-
-```sh
-cd ./references
-pnpm create next-app@latest test-cli --ts --no-eslint --tailwind --app --src-dir --import-alias "@/*"
-```
-
-4. Then once that's finished, add the `@trigger.dev/cli` to the `devDependencies` of the newly created Next.js app's `package.json` file, like so:
-
-```json
-{
-  // other package.json properties
-  "devDependencies": { "@trigger.dev/cli": "workspace:*" }
-}
-```
-
-5. Back in the terminal, navigate into the reference, and initialize the CLI. When prompted, select `self-hosted` and enter `localhost:3030` if you are testing against the local instance of Trigger.dev, or you can just use the Trigger.dev cloud. When asked for an API key, use the key you copied earlier.
-
-```sh
-cd ./test-cli
+# Build the CLI
+pnpm run build --filter trigger.dev
+# Make it accessible to `pnpm exec`
 pnpm i
-pnpm exec trigger-cli init
 ```
 
-6. If you are just testing the `init` command, you can stop here. If you'd like to test the `dev` command, first start the Next.js app on port 3000:
+5. Change into the `<root>/references/v3-catalog` directory and authorize the CLI to the local server:
 
 ```sh
-pnpm run dev
+cd references/v3-catalog
+cp .env.example .env
+pnpm exec triggerdev login -a http://localhost:3030
 ```
 
-7. Open a new terminal window, and then run the `dev` command like so:
+This will open a new browser window and authorize the CLI against your local user account.
+
+You can optionally pass a `--profile` flag to the `login` command, which will allow you to use the CLI with separate accounts/servers. We suggest using a profile called `local` for your local development:
 
 ```sh
-pnpm exec trigger-cli dev
+cd references/v3-catalog
+pnpm exec triggerdev login -a http://localhost:3030 --profile local
+# later when you run the dev or deploy command:
+pnpm exec triggerdev dev --profile local
+pnpm exec triggerdev deploy --profile local
 ```
 
-8. Please remember to delete the temporary project you created after you've tested the changes, and before you raise a PR.
+### Running
 
-## Running end-to-end webapp tests
+The following steps should be followed any time you start working on a new feature you want to test in v3:
+
+1. Make sure the webapp is running on localhost:3030
+
+2. Open a terminal window and build the CLI and watch for changes
+
+```sh
+pnpm run dev --filter trigger.dev
+```
+
+2. Open a new terminal window, and anytime changes are made to the `@trigger.dev/core` package, you'll need to manually rebuild the CLI:
+
+```sh
+pnpm run build --filter trigger.dev
+```
+
+Note: You do not need to do the same for `@trigger.dev/sdk`, just core.
+
+3. Open another terminal window, and change into the `<root>/references/v3-catalog` directory.
+
+4. Run the `dev` command, which will register all the local tasks with the platform and allow you to start testing task execution:
+
+```sh
+# in <root>/references/v3-catalog
+pnpm exec triggerdev dev
+```
+
+If you want additional debug logging, you can use the `--log-level debug` flag:
+
+```sh
+# in <root>/references/v3-catalog
+pnpm exec triggerdev dev --log-level debug
+```
+
+5. If you make any changes in the CLI/Core/SDK, you'll need to `CTRL+C` to exit the `dev` command and restart it to pickup changes. Any changes to the files inside of the `v3-catalog/src/trigger` dir will automatically be rebuilt by the `dev` command.
+
+6. Navigate to the `v3-catalog` project in your local dashboard at localhost:3030 and you should see the list of tasks.
+
+7. Go to the "Test" page in the sidebar and select a task. Then enter a payload and click "Run test". You can tell what the payloads should be by looking at the relevant task file inside the `/references/v3-catalog/src/trigger` folder. Many of them accept an empty payload.
+
+8. Feel free to add additional files in `v3-catalog/src/trigger` to test out specific aspects of the system, or add in edge cases.
+
+## Running end-to-end webapp tests (deprecated)
 
 To run the end-to-end tests, follow the steps below:
 
@@ -223,6 +221,26 @@ The end-to-end tests use a `setup` and `teardown` script to seed the database wi
 pnpm run db:studio
 ```
 
+## Adding and running migrations
+
+1. Modify packages/database/prisma/schema.prisma file
+2. Change directory to the packages/database folder
+
+   ```sh
+   cd packages/database
+   ```
+
+3. Create and apply the migrations
+
+   ```
+   pnpm run db:migrate:dev
+   ```
+
+   This creates a migration file and executes the migrations against your database and applies changes to the database schema(s)
+
+4. Commit generated migrations as well as changes to the schema.prisma file
+5. If you're using VSCode you may need to restart the Typescript server in the webapp to get updated type inference. Open a TypeScript file, then open the Command Palette (View > Command Palette) and run `TypeScript: Restart TS server`.
+
 ## Add sample jobs
 
 The [references/job-catalog](./references/job-catalog/) project defines simple jobs you can get started with.

README.md

@@ -5,16 +5,18 @@
   <img alt="Trigger.dev logo" src="https://imagedelivery.net/3TbraffuDZ4aEf8KWOmI_w/a45d1fa2-0ae8-4a39-4409-f4f934bfae00/public">
 </picture>
   
-### The open source background jobs framework
+### The open source background jobs platform
 
-[Discord](https://discord.gg/JtBAxBr2m3) | [Website](https://trigger.dev) | [Issues](https://github.com/triggerdotdev/trigger.dev/issues) | [Docs](https://trigger.dev/docs)
+[Discord](https://trigger.dev/discord) | [Website](https://trigger.dev) | [Issues](https://github.com/triggerdotdev/trigger.dev/issues) | [Docs](https://trigger.dev/docs)
 
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/triggerdotdev.svg?style=social&label=Follow%20%40trigger.dev)](https://twitter.com/triggerdotdev)
 [![GitHub Repo stars](https://img.shields.io/github/stars/triggerdotdev/trigger.dev?style=social)](https://github.com/triggerdotdev/trigger.dev)
 
 </div>
 
-# About Trigger.dev
+> The Trigger.dev v3 developer preview is now open. For more information and to get early access, check out our [developer preview launch post](https://trigger.dev/blog/v3-developer-preview-launch/).
+
+## About Trigger.dev
 
 Create long-running jobs directly in your codebase with features like API integrations, webhooks, scheduling and delays.
 
@@ -48,30 +50,6 @@ View every Task in every Run so you can tell exactly what happened.
 
 Easily integrate with hundreds of third-party APIs – including your own. Use API keys (which never leave your server) or let us handle OAuth for you. Install our integration packages and easily subscribe to webhooks and perform common tasks, or you can easily use your existing favorite Node.JS SDKs and get resumability and idempotency through our `runTask` function.
 
-## Our progress
-
-We’re building the most comprehensive and easy-to-use background jobs framework for developers.
-
-Click the links to join the discussions about our upcoming features.
-
-| Feature                                                                              | What it does                                        | Status |
-| ------------------------------------------------------------------------------------ | --------------------------------------------------- | ------ |
-| Integration kit                                                                      | Official Trigger.dev integrations or build your own | ✅     |
-| Self-hosting                                                                         | Host the platform yourself                          | ✅     |
-| Cloud                                                                                | Just write code, no deployment required             | ✅     |
-| Dashboard                                                                            | View every Task in every Run                        | ✅     |
-| Serverless                                                                           | Long-running Jobs on your serverless backend        | ✅     |
-| React hooks                                                                          | Easily update your UI with Job progress             | ✅     |
-| React frameworks                                                                     | Support for Remix, Astro, RedwoodJS & more          | ✅     |
-| [Background tasks](https://github.com/triggerdotdev/trigger.dev/discussions/400)     | Offload long or intense Tasks to our infrastructure | 🛠️     |
-| [Long-running servers](https://github.com/triggerdotdev/trigger.dev/discussions/430) | Run Jobs on your long-running backend               | 🛠️     |
-| Polling Triggers                                                                     | Subscribe to changes without webhooks               | 🕝     |
-| Vercel integration                                                                   | Easy deploy and preview environment support         | 🕝     |
-| Streaming                                                                            | Receive data from your Jobs in realtime             | 🕝     |
-| 100+ integrations                                                                    | Comprehensive support for popular APIs              | 🕝     |
-| [Trigger.dev Connect](https://github.com/triggerdotdev/trigger.dev/discussions/441)  | Use integrations signed in as your users            | 🕝     |
-| File IO                                                                              | Create Tasks that have file outputs                 | 🕝     |
-
 # Getting started
 
 Visit our docs [here](https://trigger.dev/docs).

apps/coordinator/package.json

@@ -21,8 +21,8 @@
     "execa": "^8.0.1",
     "nanoid": "^5.0.6",
     "prom-client": "^15.1.0",
-    "socket.io": "^4.7.4",
-    "socket.io-client": "^4.7.4"
+    "socket.io": "4.7.4",
+    "socket.io-client": "4.7.4"
   },
   "devDependencies": {
     "@types/node": "^18",

apps/coordinator/src/backoff.ts

@@ -0,0 +1,247 @@
+type ExponentialBackoffType = "NoJitter" | "FullJitter" | "EqualJitter";
+
+type ExponentialBackoffOptions = {
+  base: number;
+  factor: number;
+  min: number;
+  max: number;
+  maxRetries: number;
+  maxElapsed: number;
+};
+
+class StopRetrying extends Error {
+  constructor(message?: string) {
+    super(message);
+    this.name = "StopRetrying";
+  }
+}
+
+export class ExponentialBackoff {
+  #retries: number = 0;
+
+  #type: ExponentialBackoffType;
+  #base: number;
+  #factor: number;
+
+  #min: number;
+  #max: number;
+
+  #maxRetries: number;
+  #maxElapsed: number;
+
+  constructor(type?: ExponentialBackoffType, opts: Partial<ExponentialBackoffOptions> = {}) {
+    this.#type = type ?? "NoJitter";
+    this.#base = opts.base ?? 2;
+    this.#factor = opts.factor ?? 1;
+
+    this.#min = opts.min ?? -Infinity;
+    this.#max = opts.max ?? Infinity;
+
+    this.#maxRetries = opts.maxRetries ?? Infinity;
+    this.#maxElapsed = opts.maxElapsed ?? Infinity;
+  }
+
+  #clone() {
+    return new ExponentialBackoff(this.#type, {
+      base: this.#base,
+      factor: this.#factor,
+      min: this.#min,
+      max: this.#max,
+      maxRetries: this.#maxRetries,
+      maxElapsed: this.#maxElapsed,
+    });
+  }
+
+  type(type?: ExponentialBackoffType) {
+    if (typeof type !== "undefined") {
+      this.#type = type;
+    }
+    return this.#clone();
+  }
+
+  base(base?: number) {
+    if (typeof base !== "undefined") {
+      this.#base = base;
+    }
+    return this.#clone();
+  }
+
+  factor(factor?: number) {
+    if (typeof factor !== "undefined") {
+      this.#factor = factor;
+    }
+    return this.#clone();
+  }
+
+  min(min?: number) {
+    if (typeof min !== "undefined") {
+      this.#min = min;
+    }
+    return this.#clone();
+  }
+
+  max(max?: number) {
+    if (typeof max !== "undefined") {
+      this.#max = max;
+    }
+    return this.#clone();
+  }
+
+  maxRetries(maxRetries?: number) {
+    if (typeof maxRetries !== "undefined") {
+      this.#maxRetries = maxRetries;
+    }
+    return this.#clone();
+  }
+
+  maxElapsed(maxElapsed?: number) {
+    if (typeof maxElapsed !== "undefined") {
+      this.#maxElapsed = maxElapsed;
+    }
+    return this.#clone();
+  }
+
+  retries(retries?: number) {
+    if (typeof retries !== "undefined") {
+      if (retries > this.#maxRetries) {
+        console.error(
+          `Can't set retries ${retries} higher than maxRetries (${
+            this.#maxRetries
+          }), setting to maxRetries instead.`
+        );
+        this.#retries = this.#maxRetries;
+      } else {
+        this.#retries = retries;
+      }
+    }
+    return this.#clone();
+  }
+
+  async *retryAsync(maxRetries: number = this.#maxRetries ?? Infinity) {
+    let elapsed = 0;
+    let retry = 0;
+
+    while (retry <= maxRetries) {
+      const delay = this.delay(retry);
+      elapsed += delay;
+
+      if (elapsed > this.#maxElapsed) {
+        break;
+      }
+
+      yield {
+        delay: {
+          seconds: delay,
+          milliseconds: delay * 1000,
+        },
+        retry,
+      };
+
+      retry++;
+    }
+  }
+
+  async *[Symbol.asyncIterator]() {
+    yield* this.retryAsync();
+  }
+
+  delay(retries: number = this.#retries, jitter: boolean = true) {
+    if (retries > this.#maxRetries) {
+      console.error(
+        `Can't set retries ${retries} higher than maxRetries (${
+          this.#maxRetries
+        }), setting to maxRetries instead.`
+      );
+      retries = this.#maxRetries;
+    }
+
+    let delay = this.#factor * this.#base ** retries;
+
+    switch (this.#type) {
+      case "NoJitter": {
+        break;
+      }
+      case "FullJitter": {
+        if (!jitter) {
+          delay = 0;
+          break;
+        }
+
+        delay *= Math.random();
+        break;
+      }
+      case "EqualJitter": {
+        if (!jitter) {
+          delay *= 0.5;
+          break;
+        }
+
+        delay *= 0.5 * (1 + Math.random());
+        break;
+      }
+      default: {
+        throw new Error(`Unknown backoff type: ${this.#type}`);
+      }
+    }
+
+    delay = Math.min(delay, this.#max);
+    delay = Math.max(delay, this.#min);
+    delay = Math.round(delay);
+
+    return delay;
+  }
+
+  elapsed(retries: number = this.#retries, jitter: boolean = true) {
+    let elapsed = 0;
+
+    for (let i = 0; i <= retries; i++) {
+      elapsed += this.delay(i, jitter);
+    }
+
+    const total = elapsed;
+
+    let days = 0;
+    if (elapsed > 3600 * 24) {
+      days = Math.floor(elapsed / 3600 / 24);
+      elapsed -= days * 3600 * 24;
+    }
+
+    let hours = 0;
+    if (elapsed > 3600) {
+      hours = Math.floor(elapsed / 3600);
+      elapsed -= hours * 3600;
+    }
+
+    let minutes = 0;
+    if (elapsed > 60) {
+      minutes = Math.floor(elapsed / 60);
+      elapsed -= minutes * 60;
+    }
+
+    const seconds = elapsed;
+
+    return {
+      seconds,
+      minutes,
+      hours,
+      days,
+      total,
+    };
+  }
+
+  reset() {
+    this.#retries = 0;
+    return this;
+  }
+
+  next() {
+    this.#retries++;
+    return this.delay();
+  }
+
+  stop() {
+    throw new StopRetrying();
+  }
+
+  static StopRetrying = StopRetrying;
+}

apps/coordinator/src/index.ts

@@ -1,5 +1,6 @@
 import { createServer } from "node:http";
-import { $ } from "execa";
+import fs from "node:fs/promises";
+import { $, type ExecaChildProcess } from "execa";
 import { nanoid } from "nanoid";
 import { Server } from "socket.io";
 import {
@@ -8,10 +9,11 @@ import {
   PlatformToCoordinatorMessages,
   ProdWorkerSocketData,
   ProdWorkerToCoordinatorMessages,
-  ZodNamespace,
-  ZodSocketConnection,
 } from "@trigger.dev/core/v3";
+import { ZodNamespace } from "@trigger.dev/core/v3/zodNamespace";
+import { ZodSocketConnection } from "@trigger.dev/core/v3/zodSocket";
 import { HttpReply, getTextBody, SimpleLogger } from "@trigger.dev/core-apps";
+import { ExponentialBackoff } from "./backoff";
 
 import { collectDefaultMetrics, register, Gauge } from "prom-client";
 collectDefaultMetrics();
@@ -19,6 +21,26 @@ collectDefaultMetrics();
 const HTTP_SERVER_PORT = Number(process.env.HTTP_SERVER_PORT || 8020);
 const NODE_NAME = process.env.NODE_NAME || "coordinator";
 const DEFAULT_RETRY_DELAY_THRESHOLD_IN_MS = 30_000;
+const CHAOS_MONKEY_ENABLED = !!process.env.CHAOS_MONKEY_ENABLED;
+
+const FORCE_CHECKPOINT_SIMULATION = ["1", "true"].includes(
+  process.env.FORCE_CHECKPOINT_SIMULATION ?? "true"
+);
+const DISABLE_CHECKPOINT_SUPPORT = ["1", "true"].includes(
+  process.env.DISABLE_CHECKPOINT_SUPPORT ?? "false"
+);
+const SIMULATE_PUSH_FAILURE = ["1", "true"].includes(process.env.SIMULATE_PUSH_FAILURE ?? "false");
+const SIMULATE_PUSH_FAILURE_SECONDS = parseInt(
+  process.env.SIMULATE_PUSH_FAILURE_SECONDS ?? "300",
+  10
+);
+const SIMULATE_CHECKPOINT_FAILURE = ["1", "true"].includes(
+  process.env.SIMULATE_CHECKPOINT_FAILURE ?? "false"
+);
+const SIMULATE_CHECKPOINT_FAILURE_SECONDS = parseInt(
+  process.env.SIMULATE_CHECKPOINT_FAILURE_SECONDS ?? "300",
+  10
+);
 
 const REGISTRY_HOST = process.env.REGISTRY_HOST || "localhost:5000";
 const CHECKPOINT_PATH = process.env.CHECKPOINT_PATH || "/checkpoints";
@@ -32,6 +54,10 @@ const SECURE_CONNECTION = ["1", "true"].includes(process.env.SECURE_CONNECTION ?
 
 const logger = new SimpleLogger(`[${NODE_NAME}]`);
 
+if (CHAOS_MONKEY_ENABLED) {
+  logger.log("🍌 Chaos monkey enabled");
+}
+
 type CheckpointerInitializeReturn = {
   canCheckpoint: boolean;
   willSimulate: boolean;
@@ -44,11 +70,49 @@ type CheckpointAndPushOptions = {
   deploymentVersion: string;
 };
 
+type CheckpointAndPushResult =
+  | { success: true; checkpoint: CheckpointData }
+  | { success: false; reason?: "CANCELED" | "DISABLED" | "ERROR" | "IN_PROGRESS" | "NO_SUPPORT" };
+
 type CheckpointData = {
   location: string;
   docker: boolean;
 };
 
+function isExecaChildProcess(maybeExeca: unknown): maybeExeca is Awaited<ExecaChildProcess> {
+  return typeof maybeExeca === "object" && maybeExeca !== null && "escapedCommand" in maybeExeca;
+}
+
+async function getFileSize(filePath: string): Promise<number> {
+  try {
+    const stats = await fs.stat(filePath);
+    return stats.size;
+  } catch (error) {
+    console.error("Error getting file size:", error);
+    return -1;
+  }
+}
+
+async function getParsedFileSize(filePath: string) {
+  const sizeInBytes = await getFileSize(filePath);
+
+  let message = `Size in bytes: ${sizeInBytes}`;
+
+  if (sizeInBytes > 1024 * 1024) {
+    const sizeInMB = (sizeInBytes / 1024 / 1024).toFixed(2);
+    message = `Size in MB (rounded): ${sizeInMB}`;
+  } else if (sizeInBytes > 1024) {
+    const sizeInKB = (sizeInBytes / 1024).toFixed(2);
+    message = `Size in KB (rounded): ${sizeInKB}`;
+  }
+
+  return {
+    path: filePath,
+    sizeInBytes,
+    message,
+  };
+}
+
 class Checkpointer {
   #initialized = false;
   #canCheckpoint = false;
@@ -56,6 +120,8 @@ class Checkpointer {
 
   #logger = new SimpleLogger("[checkptr]");
   #abortControllers = new Map<string, AbortController>();
+  #failedCheckpoints = new Map<string, unknown>();
+  #waitingForRetry = new Set<string>();
 
   constructor(private opts = { forceSimulate: false }) {}
 
@@ -139,7 +205,7 @@ class Checkpointer {
     const start = performance.now();
     logger.log(`checkpointAndPush() start`, { start, opts });
 
-    const result = await this.#checkpointAndPush(opts);
+    const result = await this.#checkpointAndPushWithBackoff(opts);
 
     const end = performance.now();
     logger.log(`checkpointAndPush() end`, {
@@ -147,26 +213,140 @@ class Checkpointer {
       end,
       diff: end - start,
       opts,
-      success: !!result,
+      success: result.success,
     });
 
-    return result;
+    if (!result.success) {
+      return;
+    }
+
+    return result.checkpoint;
   }
 
   isCheckpointing(runId: string) {
-    return this.#abortControllers.has(runId);
+    return this.#abortControllers.has(runId) || this.#waitingForRetry.has(runId);
   }
 
-  cancelCheckpoint(runId: string) {
+  cancelCheckpoint(runId: string): boolean {
+    // If the last checkpoint failed, pretend we canceled it
+    // This ensures tasks don't wait for external resume messages to continue
+    if (this.#hasFailedCheckpoint(runId)) {
+      this.#clearFailedCheckpoint(runId);
+      return true;
+    }
+
+    if (this.#waitingForRetry.has(runId)) {
+      this.#waitingForRetry.delete(runId);
+      return true;
+    }
+
     const controller = this.#abortControllers.get(runId);
 
     if (!controller) {
       logger.debug("Nothing to cancel", { runId });
-      return;
+      return false;
     }
 
     controller.abort("cancelCheckpointing()");
     this.#abortControllers.delete(runId);
+
+    return true;
+  }
+
+  async #checkpointAndPushWithBackoff({
+    runId,
+    leaveRunning = true, // This mirrors kubernetes behaviour more accurately
+    projectRef,
+    deploymentVersion,
+  }: CheckpointAndPushOptions): Promise<CheckpointAndPushResult> {
+    this.#logger.log("Checkpointing with backoff", {
+      runId,
+      leaveRunning,
+      projectRef,
+      deploymentVersion,
+    });
+
+    const backoff = new ExponentialBackoff()
+      .type("EqualJitter")
+      .base(3)
+      .max(3 * 3600)
+      .maxElapsed(48 * 3600);
+
+    for await (const { delay, retry } of backoff) {
+      try {
+        if (retry > 0) {
+          this.#logger.error("Retrying checkpoint", {
+            runId,
+            retry,
+            delay,
+          });
+
+          this.#waitingForRetry.add(runId);
+          await new Promise((resolve) => setTimeout(resolve, delay.milliseconds));
+
+          if (!this.#waitingForRetry.has(runId)) {
+            this.#logger.log("Checkpoint canceled while waiting for retry", { runId });
+            return { success: false, reason: "CANCELED" };
+          } else {
+            this.#waitingForRetry.delete(runId);
+          }
+        }
+
+        const result = await this.#checkpointAndPush({
+          runId,
+          leaveRunning,
+          projectRef,
+          deploymentVersion,
+        });
+
+        if (result.success) {
+          return result;
+        }
+
+        if (result.reason === "CANCELED") {
+          this.#logger.log("Checkpoint canceled, won't retry", { runId });
+          // Don't fail the checkpoint, as it was canceled
+          return result;
+        }
+
+        if (result.reason === "IN_PROGRESS") {
+          this.#logger.log("Checkpoint already in progress, won't retry", { runId });
+          this.#failCheckpoint(runId, result.reason);
+          return result;
+        }
+
+        if (result.reason === "NO_SUPPORT") {
+          this.#logger.log("No checkpoint support, won't retry", { runId });
+          this.#failCheckpoint(runId, result.reason);
+          return result;
+        }
+
+        if (result.reason === "DISABLED") {
+          this.#logger.log("Checkpoint support disabled, won't retry", { runId });
+          this.#failCheckpoint(runId, result.reason);
+          return result;
+        }
+
+        continue;
+      } catch (error) {
+        this.#logger.error("Checkpoint error", {
+          retry,
+          runId,
+          delay,
+          error: error instanceof Error ? error.message : error,
+        });
+      }
+    }
+
+    this.#logger.error(`Checkpoint failed after exponential backoff`, {
+      runId,
+      leaveRunning,
+      projectRef,
+      deploymentVersion,
+    });
+    this.#failCheckpoint(runId, "ERROR");
+
+    return { success: false, reason: "ERROR" };
   }
 
   async #checkpointAndPush({
@@ -174,24 +354,32 @@ class Checkpointer {
     leaveRunning = true, // This mirrors kubernetes behaviour more accurately
     projectRef,
     deploymentVersion,
-  }: CheckpointAndPushOptions): Promise<CheckpointData | undefined> {
+  }: CheckpointAndPushOptions): Promise<CheckpointAndPushResult> {
     await this.initialize();
 
+    const options = {
+      runId,
+      leaveRunning,
+      projectRef,
+      deploymentVersion,
+    };
+
     if (!this.#dockerMode && !this.#canCheckpoint) {
       this.#logger.error("No checkpoint support. Simulation requires docker.");
-      return;
+      return { success: false, reason: "NO_SUPPORT" };
     }
 
     if (this.#abortControllers.has(runId)) {
-      logger.error("Checkpoint procedure already in progress", {
-        options: {
-          runId,
-          leaveRunning,
-          projectRef,
-          deploymentVersion,
-        },
-      });
-      return;
+      logger.error("Checkpoint procedure already in progress", { options });
+      return { success: false, reason: "IN_PROGRESS" };
+    }
+
+    // This is a new checkpoint, clear any last failure for this run
+    this.#clearFailedCheckpoint(runId);
+
+    if (DISABLE_CHECKPOINT_SUPPORT) {
+      this.#logger.error("Checkpoint support disabled", { options });
+      return { success: false, reason: "DISABLED" };
     }
 
     const controller = new AbortController();
@@ -199,19 +387,44 @@ class Checkpointer {
 
     const $$ = $({ signal: controller.signal });
 
-    try {
-      const shortCode = nanoid(8);
-      const imageRef = this.#getImageRef(projectRef, deploymentVersion, shortCode);
-      const exportLocation = this.#getExportLocation(projectRef, deploymentVersion, shortCode);
+    const shortCode = nanoid(8);
+    const imageRef = this.#getImageRef(projectRef, deploymentVersion, shortCode);
+    const exportLocation = this.#getExportLocation(projectRef, deploymentVersion, shortCode);
 
-      this.#logger.log("Checkpointing:", {
-        options: {
-          runId,
-          leaveRunning,
-          projectRef,
-          deploymentVersion,
-        },
-      });
+    const cleanup = async () => {
+      if (this.#dockerMode) {
+        return;
+      }
+
+      try {
+        await $`rm ${exportLocation}`;
+        this.#logger.log("Deleted checkpoint archive", { exportLocation });
+
+        await $`buildah rmi ${imageRef}`;
+        this.#logger.log("Deleted checkpoint image", { imageRef });
+      } catch (error) {
+        this.#logger.error("Failure during checkpoint cleanup", { exportLocation, error });
+      }
+    };
+
+    try {
+      if (CHAOS_MONKEY_ENABLED) {
+        console.log("🍌 Chaos monkey wreaking havoc");
+
+        const random = Math.random();
+
+        if (random < 0.33) {
+          // Fake long checkpoint duration
+          await $$`sleep 300`;
+        } else if (random < 0.66) {
+          // Fake checkpoint error
+          await $$`false`;
+        } else {
+          // no-op
+        }
+      }
+
+      this.#logger.log("Checkpointing:", { options });
 
       const containterName = this.#getRunContainerName(runId);
 
@@ -222,6 +435,13 @@ class Checkpointer {
             this.#logger.log("Simulating checkpoint");
             this.#logger.debug(await $$`docker pause ${containterName}`);
           } else {
+            if (SIMULATE_CHECKPOINT_FAILURE) {
+              if (performance.now() < SIMULATE_CHECKPOINT_FAILURE_SECONDS * 1000) {
+                this.#logger.error("Simulating checkpoint failure", { options });
+                throw new Error("SIMULATE_CHECKPOINT_FAILURE");
+              }
+            }
+
             if (leaveRunning) {
               this.#logger.debug(
                 await $$`docker checkpoint create --leave-running ${containterName} ${exportLocation}`
@@ -232,9 +452,9 @@ class Checkpointer {
               );
             }
           }
-        } catch (error: any) {
-          this.#logger.error(error.stderr);
-          return;
+        } catch (error) {
+          this.#logger.error("Failed while creating docker checkpoint", { exportLocation });
+          throw error;
         }
 
         this.#logger.log("checkpoint created:", {
@@ -243,8 +463,11 @@ class Checkpointer {
         });
 
         return {
-          location: exportLocation,
-          docker: true,
+          success: true,
+          checkpoint: {
+            location: exportLocation,
+            docker: true,
+          },
         };
       }
 
@@ -264,54 +487,105 @@ class Checkpointer {
         throw new Error("could not find container id");
       }
 
+      const start = performance.now();
+
+      if (SIMULATE_CHECKPOINT_FAILURE) {
+        if (performance.now() < SIMULATE_CHECKPOINT_FAILURE_SECONDS * 1000) {
+          this.#logger.error("Simulating checkpoint failure", { options });
+          throw new Error("SIMULATE_CHECKPOINT_FAILURE");
+        }
+      }
+
+      // Create checkpoint
       this.#logger.debug(await $$`crictl checkpoint --export=${exportLocation} ${containerId}`);
+      const postCheckpoint = performance.now();
+
+      // Print checkpoint size
+      const size = await getParsedFileSize(exportLocation);
+      this.#logger.log("checkpoint archive created", { size, options });
 
       // Create image from checkpoint
       const container = this.#logger.debug(await $$`buildah from scratch`);
+      const postFrom = performance.now();
+
       this.#logger.debug(await $$`buildah add ${container} ${exportLocation} /`);
+      const postAdd = performance.now();
+
       this.#logger.debug(
         await $$`buildah config --annotation=io.kubernetes.cri-o.annotations.checkpoint.name=counter ${container}`
       );
+      const postConfig = performance.now();
+
       this.#logger.debug(await $$`buildah commit ${container} ${imageRef}`);
+      const postCommit = performance.now();
+
       this.#logger.debug(await $$`buildah rm ${container}`);
+      const postRm = performance.now();
+
+      if (SIMULATE_PUSH_FAILURE) {
+        if (performance.now() < SIMULATE_PUSH_FAILURE_SECONDS * 1000) {
+          this.#logger.error("Simulating push failure", { options });
+          throw new Error("SIMULATE_PUSH_FAILURE");
+        }
+      }
 
       // Push checkpoint image
       this.#logger.debug(await $$`buildah push --tls-verify=${REGISTRY_TLS_VERIFY} ${imageRef}`);
+      const postPush = performance.now();
 
-      this.#logger.log("Checkpointed and pushed image to:", { location: imageRef });
+      const perf = {
+        "crictl checkpoint": postCheckpoint - start,
+        "buildah from": postFrom - postCheckpoint,
+        "buildah add": postAdd - postFrom,
+        "buildah config": postConfig - postAdd,
+        "buildah commit": postCommit - postConfig,
+        "buildah rm": postRm - postCommit,
+        "buildah push": postPush - postRm,
+      };
 
-      try {
-        await $$`rm ${exportLocation}`;
-        this.#logger.log("Deleted checkpoint archive", { exportLocation });
-
-        // Disabled for now as this will increase restore time by having to pull the image again
-        // await $`buildah rmi ${imageRef}`;
-        // this.#logger.log("Deleted checkpoint image", { imageRef });
-      } catch (error) {
-        this.#logger.error("Failed during checkpoint cleanup", { exportLocation });
-        this.#logger.debug(error);
-      }
+      this.#logger.log("Checkpointed and pushed image to:", { location: imageRef, perf });
 
       return {
-        location: imageRef,
-        docker: false,
+        success: true,
+        checkpoint: {
+          location: imageRef,
+          docker: false,
+        },
       };
     } catch (error) {
-      this.#logger.error("checkpoint failed", {
-        options: {
-          runId,
-          leaveRunning,
-          projectRef,
-          deploymentVersion,
-        },
-        error,
-      });
-      return;
+      if (isExecaChildProcess(error)) {
+        if (error.isCanceled) {
+          this.#logger.error("Checkpoint canceled", { options, error });
+
+          return { success: false, reason: "CANCELED" };
+        }
+
+        this.#logger.error("Checkpoint command error", { options, error });
+
+        return { success: false, reason: "ERROR" };
+      }
+
+      this.#logger.error("Unhandled checkpoint error", { options, error });
+
+      return { success: false, reason: "ERROR" };
     } finally {
       this.#abortControllers.delete(runId);
+      await cleanup();
     }
   }
 
+  #failCheckpoint(runId: string, error: unknown) {
+    this.#failedCheckpoints.set(runId, error);
+  }
+
+  #clearFailedCheckpoint(runId: string) {
+    this.#failedCheckpoints.delete(runId);
+  }
+
+  #hasFailedCheckpoint(runId: string) {
+    return this.#failedCheckpoints.has(runId);
+  }
+
   #getRunContainerName(suffix: string) {
     return `task-run-${suffix}`;
   }
@@ -319,7 +593,7 @@ class Checkpointer {
 
 class TaskCoordinator {
   #httpServer: ReturnType<typeof createServer>;
-  #checkpointer = new Checkpointer({ forceSimulate: true });
+  #checkpointer = new Checkpointer({ forceSimulate: FORCE_CHECKPOINT_SIMULATION });
 
   #prodWorkerNamespace: ZodNamespace<
     typeof ProdWorkerToCoordinatorMessages,
@@ -440,6 +714,30 @@ class TaskCoordinator {
 
           taskSocket.emit("REQUEST_ATTEMPT_CANCELLATION", message);
         },
+        REQUEST_RUN_CANCELLATION: async (message) => {
+          const taskSocket = await this.#getRunSocket(message.runId);
+
+          if (!taskSocket) {
+            logger.log("Socket for run not found", {
+              runId: message.runId,
+            });
+            return;
+          }
+
+          this.#checkpointer.cancelCheckpoint(message.runId);
+
+          if (message.delayInMs) {
+            taskSocket.emit("REQUEST_EXIT", {
+              version: "v2",
+              delayInMs: message.delayInMs,
+            });
+          } else {
+            // If there's no delay, assume the worker doesn't support non-v1 messages
+            taskSocket.emit("REQUEST_EXIT", {
+              version: "v1",
+            });
+          }
+        },
         READY_FOR_RETRY: async (message) => {
           const taskSocket = await this.#getRunSocket(message.runId);
 
@@ -526,6 +824,20 @@ class TaskCoordinator {
       onConnection: async (socket, handler, sender) => {
         const logger = new SimpleLogger(`[prod-worker][${socket.id}]`);
 
+        const crashRun = async (error: { name: string; message: string; stack?: string }) => {
+          try {
+            this.#platformSocket?.send("RUN_CRASHED", {
+              version: "v1",
+              runId: socket.data.runId,
+              error,
+            });
+          } finally {
+            socket.emit("REQUEST_EXIT", {
+              version: "v1",
+            });
+          }
+        };
+
         const checkpointInProgress = () => {
           return this.#checkpointableTasks.has(socket.data.runId);
         };
@@ -594,8 +906,9 @@ class TaskCoordinator {
             if (!executionAck) {
               logger.error("no execution ack", { runId: socket.data.runId });
 
-              socket.emit("REQUEST_EXIT", {
-                version: "v1",
+              await crashRun({
+                name: "ReadyForExecutionError",
+                message: "No execution ack",
               });
 
               return;
@@ -604,8 +917,9 @@ class TaskCoordinator {
             if (!executionAck.success) {
               logger.error("failed to get execution payload", { runId: socket.data.runId });
 
-              socket.emit("REQUEST_EXIT", {
-                version: "v1",
+              await crashRun({
+                name: "ReadyForExecutionError",
+                message: "Failed to get execution payload",
               });
 
               return;
@@ -619,6 +933,62 @@ class TaskCoordinator {
             socket.data.attemptFriendlyId = executionAck.payload.execution.attempt.id;
           } catch (error) {
             logger.error("Error", { error });
+
+            await crashRun({
+              name: "ReadyForExecutionError",
+              message:
+                error instanceof Error ? `Unexpected error: ${error.message}` : "Unexpected error",
+            });
+
+            return;
+          }
+        });
+
+        socket.on("READY_FOR_LAZY_ATTEMPT", async (message) => {
+          logger.log("[READY_FOR_LAZY_ATTEMPT]", message);
+
+          try {
+            const lazyAttempt = await this.#platformSocket?.sendWithAck("READY_FOR_LAZY_ATTEMPT", {
+              ...message,
+              envId: socket.data.envId,
+            });
+
+            if (!lazyAttempt) {
+              logger.error("no lazy attempt ack", { runId: socket.data.runId });
+
+              await crashRun({
+                name: "ReadyForLazyAttemptError",
+                message: "No lazy attempt ack",
+              });
+
+              return;
+            }
+
+            if (!lazyAttempt.success) {
+              logger.error("failed to get lazy attempt payload", { runId: socket.data.runId });
+
+              await crashRun({
+                name: "ReadyForLazyAttemptError",
+                message: "Failed to get lazy attempt payload",
+              });
+
+              return;
+            }
+
+            socket.emit("EXECUTE_TASK_RUN_LAZY_ATTEMPT", {
+              version: "v1",
+              lazyPayload: lazyAttempt.lazyPayload,
+            });
+          } catch (error) {
+            logger.error("Error", { error });
+
+            await crashRun({
+              name: "ReadyForLazyAttemptError",
+              message:
+                error instanceof Error ? `Unexpected error: ${error.message}` : "Unexpected error",
+            });
+
+            return;
           }
         });
 
@@ -712,6 +1082,19 @@ class TaskCoordinator {
           }
         });
 
+        socket.on("TASK_RUN_FAILED_TO_RUN", async ({ completion }) => {
+          logger.log("completed task", { completionId: completion.id });
+
+          this.#platformSocket?.send("TASK_RUN_FAILED_TO_RUN", {
+            version: "v1",
+            completion,
+          });
+
+          socket.emit("REQUEST_EXIT", {
+            version: "v1",
+          });
+        });
+
         socket.on("READY_FOR_CHECKPOINT", async (message) => {
           logger.log("[READY_FOR_CHECKPOINT]", message);
 
@@ -725,10 +1108,18 @@ class TaskCoordinator {
           checkpointable.resolve();
         });
 
-        socket.on("CANCEL_CHECKPOINT", async (message) => {
+        socket.on("CANCEL_CHECKPOINT", async (message, callback) => {
           logger.log("[CANCEL_CHECKPOINT]", message);
 
-          this.#cancelCheckpoint(socket.data.runId);
+          if (message.version === "v1") {
+            this.#cancelCheckpoint(socket.data.runId);
+            // v1 has no callback
+            return;
+          }
+
+          const checkpointCanceled = this.#cancelCheckpoint(socket.data.runId);
+
+          callback({ version: "v2", checkpointCanceled });
         });
 
         socket.on("WAIT_FOR_DURATION", async (message, callback) => {
@@ -880,7 +1271,7 @@ class TaskCoordinator {
           logger.log("[INDEX_TASKS]", message);
 
           const workerAck = await this.#platformSocket?.sendWithAck("CREATE_WORKER", {
-            version: "v1",
+            version: "v2",
             projectRef: socket.data.projectRef,
             envId: socket.data.envId,
             deploymentId: message.deploymentId,
@@ -889,6 +1280,7 @@ class TaskCoordinator {
               packageVersion: message.packageVersion,
               tasks: message.tasks,
             },
+            supportsLazyAttempts: message.version !== "v1" && message.supportsLazyAttempts,
           });
 
           if (!workerAck) {
@@ -907,6 +1299,34 @@ class TaskCoordinator {
             error: message.error,
           });
         });
+
+        socket.on("CREATE_TASK_RUN_ATTEMPT", async (message, callback) => {
+          logger.log("[CREATE_TASK_RUN_ATTEMPT]", message);
+
+          const createAttempt = await this.#platformSocket?.sendWithAck("CREATE_TASK_RUN_ATTEMPT", {
+            runId: message.runId,
+            envId: socket.data.envId,
+          });
+
+          if (!createAttempt?.success) {
+            logger.debug("no ack while creating attempt", message);
+            callback({ success: false });
+            return;
+          }
+
+          socket.data.attemptFriendlyId = createAttempt.executionPayload.execution.attempt.id;
+
+          callback({
+            success: true,
+            executionPayload: createAttempt.executionPayload,
+          });
+        });
+
+        socket.on("UNRECOVERABLE_ERROR", async (message) => {
+          logger.log("[UNRECOVERABLE_ERROR]", message);
+
+          await crashRun(message.error);
+        });
       },
       onDisconnect: async (socket, handler, sender, logger) => {
         this.#platformSocket?.send("LOG", {
@@ -918,13 +1338,16 @@ class TaskCoordinator {
         TASK_HEARTBEAT: async (message) => {
           this.#platformSocket?.send("TASK_HEARTBEAT", message);
         },
+        TASK_RUN_HEARTBEAT: async (message) => {
+          this.#platformSocket?.send("TASK_RUN_HEARTBEAT", message);
+        },
       },
     });
 
     return provider;
   }
 
-  #cancelCheckpoint(runId: string) {
+  #cancelCheckpoint(runId: string): boolean {
     const checkpointWait = this.#checkpointableTasks.get(runId);
 
     if (checkpointWait) {
@@ -933,7 +1356,11 @@ class TaskCoordinator {
     }
 
     // Cancel checkpointing procedure
-    this.#checkpointer.cancelCheckpoint(runId);
+    const checkpointCanceled = this.#checkpointer.cancelCheckpoint(runId);
+
+    logger.log("cancelCheckpoint()", { runId, checkpointCanceled });
+
+    return checkpointCanceled;
   }
 
   #createHttpServer() {

apps/docker-provider/.env.example

@@ -4,6 +4,8 @@ PLATFORM_WS_PORT=3030
 PLATFORM_SECRET=provider-secret
 SECURE_CONNECTION=false
 
+OTEL_EXPORTER_OTLP_ENDPOINT=http://0.0.0.0:3030/otel
+
 # Use this if you are on macOS
 # COORDINATOR_HOST="host.docker.internal"
 # OTEL_EXPORTER_OTLP_ENDPOINT="http://host.docker.internal:4318"

apps/docker-provider/src/index.ts

@@ -13,9 +13,14 @@ import { PostStartCauses, PreStopCauses } from "@trigger.dev/core/v3";
 const MACHINE_NAME = process.env.MACHINE_NAME || "local";
 const COORDINATOR_PORT = process.env.COORDINATOR_PORT || 8020;
 const COORDINATOR_HOST = process.env.COORDINATOR_HOST || "127.0.0.1";
+
 const OTEL_EXPORTER_OTLP_ENDPOINT =
   process.env.OTEL_EXPORTER_OTLP_ENDPOINT || "http://0.0.0.0:4318";
 
+const FORCE_CHECKPOINT_SIMULATION = ["1", "true"].includes(
+  process.env.FORCE_CHECKPOINT_SIMULATION ?? "true"
+);
+
 const logger = new SimpleLogger(`[${MACHINE_NAME}]`);
 
 type InitializeReturn = {
@@ -257,6 +262,7 @@ class DockerTaskOperations implements TaskOperations {
       return await execa("docker", [
         "exec",
         containerName,
+        "busybox",
         "wget",
         "-q",
         "-O-",
@@ -277,7 +283,7 @@ class DockerTaskOperations implements TaskOperations {
 }
 
 const provider = new ProviderShell({
-  tasks: new DockerTaskOperations({ forceSimulate: true }),
+  tasks: new DockerTaskOperations({ forceSimulate: FORCE_CHECKPOINT_SIMULATION }),
   type: "docker",
 });
 

apps/kubernetes-provider/src/index.ts

@@ -10,6 +10,7 @@ import {
 import { Machine, PostStartCauses, PreStopCauses, EnvironmentType } from "@trigger.dev/core/v3";
 import { randomUUID } from "crypto";
 import { TaskMonitor } from "./taskMonitor";
+import { PodCleaner } from "./podCleaner";
 
 const RUNTIME_ENV = process.env.KUBERNETES_PORT ? "kubernetes" : "local";
 const NODE_NAME = process.env.NODE_NAME || "local";
@@ -80,8 +81,8 @@ class KubernetesTaskOperations implements TaskOperations {
                   ],
                   resources: {
                     limits: {
-                      cpu: "250m",
-                      memory: "0.5G",
+                      cpu: "1",
+                      memory: "1G",
                       "ephemeral-storage": "2Gi",
                     },
                   },
@@ -133,6 +134,7 @@ class KubernetesTaskOperations implements TaskOperations {
         },
         spec: {
           ...this.#defaultPodSpec,
+          terminationGracePeriodSeconds: 60 * 60,
           containers: [
             {
               name: this.#getRunContainerName(opts.runId),
@@ -210,7 +212,8 @@ class KubernetesTaskOperations implements TaskOperations {
             },
             {
               name: "populate-taskinfo",
-              image: "busybox",
+              image: "registry.digitalocean.com/trigger/busybox",
+              imagePullPolicy: "IfNotPresent",
               command: ["/bin/sh", "-c"],
               args: ["printenv COORDINATOR_HOST | tee /etc/taskinfo/coordinator-host"],
               env: [
@@ -313,6 +316,9 @@ class KubernetesTaskOperations implements TaskOperations {
         {
           name: "registry-trigger",
         },
+        {
+          name: "registry-trigger-failover",
+        },
       ],
       nodeSelector: {
         nodetype: "worker",
@@ -409,7 +415,7 @@ class KubernetesTaskOperations implements TaskOperations {
       `for i in $(seq ${retries}); do sleep 1; busybox wget -q -O- 127.0.0.1:8000/${type}?cause=${cause} && break; done`,
     ];
 
-    logger.log("getLifecycleCommand()", { exec });
+    logger.debug("getLifecycleCommand()", { exec });
 
     return exec;
   }
@@ -541,3 +547,11 @@ const taskMonitor = new TaskMonitor({
 });
 
 taskMonitor.start();
+
+const podCleaner = new PodCleaner({
+  runtimeEnv: RUNTIME_ENV,
+  namespace: "default",
+  intervalInSeconds: 300,
+});
+
+podCleaner.start();

apps/kubernetes-provider/src/podCleaner.ts

@@ -0,0 +1,264 @@
+import * as k8s from "@kubernetes/client-node";
+import { SimpleLogger } from "@trigger.dev/core-apps";
+
+type PodCleanerOptions = {
+  runtimeEnv: "local" | "kubernetes";
+  namespace?: string;
+  intervalInSeconds?: number;
+};
+
+export class PodCleaner {
+  private enabled = false;
+  private namespace = "default";
+  private intervalInSeconds = 300;
+
+  private logger = new SimpleLogger("[PodCleaner]");
+  private k8sClient: {
+    core: k8s.CoreV1Api;
+    kubeConfig: k8s.KubeConfig;
+  };
+
+  constructor(private opts: PodCleanerOptions) {
+    if (opts.namespace) {
+      this.namespace = opts.namespace;
+    }
+
+    if (opts.intervalInSeconds) {
+      this.intervalInSeconds = opts.intervalInSeconds;
+    }
+
+    this.k8sClient = this.#createK8sClient();
+  }
+
+  #createK8sClient() {
+    const kubeConfig = new k8s.KubeConfig();
+
+    if (this.opts.runtimeEnv === "local") {
+      kubeConfig.loadFromDefault();
+    } else if (this.opts.runtimeEnv === "kubernetes") {
+      kubeConfig.loadFromCluster();
+    } else {
+      throw new Error(`Unsupported runtime environment: ${this.opts.runtimeEnv}`);
+    }
+
+    return {
+      core: kubeConfig.makeApiClient(k8s.CoreV1Api),
+      kubeConfig: kubeConfig,
+    };
+  }
+
+  #isRecord(candidate: unknown): candidate is Record<string, unknown> {
+    if (typeof candidate !== "object" || candidate === null) {
+      return false;
+    } else {
+      return true;
+    }
+  }
+
+  #logK8sError(err: unknown, debugOnly = false) {
+    if (debugOnly) {
+      this.logger.debug("K8s API Error", err);
+    } else {
+      this.logger.error("K8s API Error", err);
+    }
+  }
+
+  #handleK8sError(err: unknown) {
+    if (!this.#isRecord(err) || !this.#isRecord(err.body)) {
+      this.#logK8sError(err);
+      return;
+    }
+
+    this.#logK8sError(err, true);
+
+    if (typeof err.body.message === "string") {
+      this.#logK8sError({ message: err.body.message });
+      return;
+    }
+
+    this.#logK8sError({ body: err.body });
+  }
+
+  async #deletePods(opts: {
+    namespace: string;
+    dryRun?: boolean;
+    fieldSelector?: string;
+    labelSelector?: string;
+  }) {
+    return await this.k8sClient.core
+      .deleteCollectionNamespacedPod(
+        opts.namespace,
+        undefined, // pretty
+        undefined, // continue
+        opts.dryRun ? "All" : undefined,
+        opts.fieldSelector,
+        undefined, // gracePeriodSeconds
+        opts.labelSelector
+      )
+      .catch(this.#handleK8sError.bind(this));
+  }
+
+  async #deleteCompletedRuns() {
+    this.logger.log("Deleting completed runs");
+
+    const start = Date.now();
+
+    const result = await this.#deletePods({
+      namespace: this.namespace,
+      fieldSelector: "status.phase=Succeeded",
+      labelSelector: "app=task-run",
+    });
+
+    const elapsedMs = Date.now() - start;
+
+    if (!result) {
+      this.logger.log("Deleting completed runs: No delete result", { elapsedMs });
+      return;
+    }
+
+    const total = (result.response as any)?.body?.items?.length ?? 0;
+
+    this.logger.log("Deleting completed runs: Done", { total, elapsedMs });
+  }
+
+  async #deleteFailedRuns() {
+    this.logger.log("Deleting failed runs");
+
+    const start = Date.now();
+
+    const result = await this.#deletePods({
+      namespace: this.namespace,
+      fieldSelector: "status.phase=Failed",
+      labelSelector: "app=task-run",
+    });
+
+    const elapsedMs = Date.now() - start;
+
+    if (!result) {
+      this.logger.log("Deleting failed runs: No delete result", { elapsedMs });
+      return;
+    }
+
+    const total = (result.response as any)?.body?.items?.length ?? 0;
+
+    this.logger.log("Deleting failed runs: Done", { total, elapsedMs });
+  }
+
+  async #deleteUnrecoverableRuns() {
+    await this.#deletePods({
+      namespace: this.namespace,
+      fieldSelector: "status.phase=?",
+      labelSelector: "app=task-run",
+    });
+  }
+
+  async start() {
+    this.enabled = true;
+    this.logger.log("Starting");
+
+    const completedInterval = setInterval(async () => {
+      if (!this.enabled) {
+        clearInterval(completedInterval);
+        return;
+      }
+
+      try {
+        await this.#deleteCompletedRuns();
+      } catch (error) {
+        this.logger.error("Error deleting completed runs", error);
+      }
+    }, this.intervalInSeconds * 1000);
+
+    const failedInterval = setInterval(
+      async () => {
+        if (!this.enabled) {
+          clearInterval(failedInterval);
+          return;
+        }
+
+        try {
+          await this.#deleteFailedRuns();
+        } catch (error) {
+          this.logger.error("Error deleting completed runs", error);
+        }
+      },
+      // Use a longer interval for failed runs. This is only a backup in case the task monitor fails.
+      2 * this.intervalInSeconds * 1000
+    );
+
+    // this.#launchTests();
+  }
+
+  async stop() {
+    if (!this.enabled) {
+      return;
+    }
+
+    this.enabled = false;
+    this.logger.log("Shutting down..");
+  }
+
+  async #launchTests() {
+    const createPod = async (
+      container: k8s.V1Container,
+      name: string,
+      labels?: Record<string, string>
+    ) => {
+      this.logger.log("Creating pod:", name);
+
+      const pod = {
+        metadata: {
+          name,
+          labels,
+        },
+        spec: {
+          restartPolicy: "Never",
+          automountServiceAccountToken: false,
+          terminationGracePeriodSeconds: 1,
+          containers: [container],
+        },
+      } satisfies k8s.V1Pod;
+
+      await this.k8sClient.core
+        .createNamespacedPod(this.namespace, pod)
+        .catch(this.#handleK8sError.bind(this));
+    };
+
+    const createIdlePod = async (name: string, labels?: Record<string, string>) => {
+      const container = {
+        name,
+        image: "docker.io/library/busybox",
+        command: ["sh"],
+        args: ["-c", "sleep infinity"],
+      } satisfies k8s.V1Container;
+
+      await createPod(container, name, labels);
+    };
+
+    const createCompletedPod = async (name: string, labels?: Record<string, string>) => {
+      const container = {
+        name,
+        image: "docker.io/library/busybox",
+        command: ["sh"],
+        args: ["-c", "true"],
+      } satisfies k8s.V1Container;
+
+      await createPod(container, name, labels);
+    };
+
+    const createFailedPod = async (name: string, labels?: Record<string, string>) => {
+      const container = {
+        name,
+        image: "docker.io/library/busybox",
+        command: ["sh"],
+        args: ["-c", "false"],
+      } satisfies k8s.V1Container;
+
+      await createPod(container, name, labels);
+    };
+
+    await createIdlePod("test-idle-1", { app: "task-run" });
+    await createFailedPod("test-failed-1", { app: "task-run" });
+    await createCompletedPod("test-completed-1", { app: "task-run" });
+  }
+}

apps/kubernetes-provider/src/taskMonitor.ts

@@ -30,10 +30,12 @@ type TaskMonitorOptions = {
 
 export class TaskMonitor {
   #enabled = false;
+
   #logger = new SimpleLogger("[TaskMonitor]");
   #taskInformer: ReturnType<typeof k8s.makeInformer<k8s.V1Pod>>;
   #processedPods = new Map<string, number>();
   #queue = new PQueue({ concurrency: 10 });
+
   #k8sClient: {
     core: k8s.CoreV1Api;
     kubeConfig: k8s.KubeConfig;
@@ -44,6 +46,10 @@ export class TaskMonitor {
   private labelSelector = "app in (task-index, task-run)";
 
   constructor(private opts: TaskMonitorOptions) {
+    if (opts.namespace) {
+      this.namespace = opts.namespace;
+    }
+
     this.#k8sClient = this.#createK8sClient();
 
     this.#taskInformer = this.#createTaskInformer();
@@ -136,6 +142,13 @@ export class TaskMonitor {
 
     const podStatus = this.#getPodStatusSummary(pod.status);
     const containerState = this.#getContainerStateSummary(containerStatus.state);
+    const exitCode = containerState.exitCode ?? -1;
+
+    // We use this special exit code to signal any errors were already handled elsewhere
+    if (exitCode === 111) {
+      return;
+    }
+
     const rawLogs = await this.#getLogTail(podName);
 
     this.#logger.log(`${podName} failed with:`, {
@@ -144,7 +157,6 @@ export class TaskMonitor {
       rawLogs,
     });
 
-    const exitCode = containerState.exitCode ?? -1;
     const rawReason = podStatus.reason ?? containerState.reason ?? "";
     const message = podStatus.message ?? containerState.message ?? "";
 
@@ -402,7 +414,7 @@ export class TaskMonitor {
     const createNonZeroExitPod = async (name: string, labels?: Record<string, string>) => {
       const container = {
         name,
-        image: "busybox",
+        image: "docker.io/library/busybox",
         command: ["sh"],
         args: ["-c", "exit 1"],
       } satisfies k8s.V1Container;
@@ -413,7 +425,7 @@ export class TaskMonitor {
     const createOoDiskPod = async (name: string, labels?: Record<string, string>) => {
       const container = {
         name,
-        image: "busybox",
+        image: "docker.io/library/busybox",
         command: ["sh"],
         args: [
           "-c",

apps/proxy/package.json

@@ -7,9 +7,9 @@
     "dev": "wrangler dev"
   },
   "devDependencies": {
-    "@cloudflare/workers-types": "^4.20230419.0",
+    "@cloudflare/workers-types": "^4.20240512.0",
     "typescript": "^5.0.4",
-    "wrangler": "^3.0.0"
+    "wrangler": "^3.57.1"
   },
   "dependencies": {
     "@aws-sdk/client-sqs": "^3.445.0",

apps/proxy/src/index.ts

@@ -1,5 +1,7 @@
 import { queueEvent } from "./events/queueEvent";
 import { queueEvents } from "./events/queueEvents";
+import { applyRateLimit } from "./rateLimit";
+import { Ratelimit } from "./rateLimiter";
 
 export interface Env {
   /** The hostname needs to be changed to allow requests to pass to the Trigger.dev platform */
@@ -9,6 +11,8 @@ export interface Env {
   AWS_SQS_SECRET_ACCESS_KEY: string;
   AWS_SQS_QUEUE_URL: string;
   AWS_SQS_REGION: string;
+  //rate limiter
+  API_RATE_LIMITER: Ratelimit;
 }
 
 export default {
@@ -25,13 +29,13 @@ export default {
     switch (url.pathname) {
       case "/api/v1/events": {
         if (request.method === "POST") {
-          return queueEvent(request, env);
+          return applyRateLimit(request, env, () => queueEvent(request, env));
         }
         break;
       }
       case "/api/v1/events/bulk": {
         if (request.method === "POST") {
-          return queueEvents(request, env);
+          return applyRateLimit(request, env, () => queueEvents(request, env));
         }
         break;
       }

apps/proxy/src/rateLimit.ts

@@ -0,0 +1,46 @@
+import { Env } from "src";
+import { getApiKeyFromRequest } from "./apikey";
+import { json } from "./json";
+
+export async function applyRateLimit(
+  request: Request,
+  env: Env,
+  fn: () => Promise<Response>
+): Promise<Response> {
+  const apiKey = getApiKeyFromRequest(request);
+  if (apiKey) {
+    const result = await env.API_RATE_LIMITER.limit({ key: `apikey-${apiKey.apiKey}` });
+    const { success } = result;
+    console.log(`Rate limiter`, {
+      success,
+      key: `${apiKey.apiKey.substring(0, 12)}...`,
+    });
+    if (!success) {
+      //60s in the future
+      const reset = Date.now() + 60 * 1000;
+      const secondsUntilReset = Math.max(0, (reset - new Date().getTime()) / 1000);
+
+      return json(
+        {
+          title: "Rate Limit Exceeded",
+          status: 429,
+          type: "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429",
+          detail: `Rate limit exceeded. Retry in ${secondsUntilReset} seconds.`,
+          error: `Rate limit exceeded. Retry in ${secondsUntilReset} seconds.`,
+          reset,
+        },
+        {
+          status: 429,
+          headers: {
+            "x-ratelimit-reset": reset.toString(),
+          },
+        }
+      );
+    }
+  } else {
+    console.log(`Rate limiter: no API key for request`);
+  }
+
+  //call the original function
+  return fn();
+}

apps/proxy/src/rateLimiter.ts

@@ -0,0 +1,23 @@
+export interface Ratelimit {
+  /*
+   * The ratelimit function
+   * @param {RatelimitOptions} options
+   * @returns {Promise<RatelimitResponse>}
+   */
+  limit: (options: RatelimitOptions) => Promise<RatelimitResponse>;
+}
+
+export interface RatelimitOptions {
+  /*
+   * The key to identify the user, can be an IP address, user ID, etc.
+   */
+  key: string;
+}
+
+export interface RatelimitResponse {
+  /*
+   * The ratelimit success status
+   * @returns {boolean}
+   */
+  success: boolean;
+}

apps/proxy/wrangler.toml

@@ -1,7 +1,33 @@
 name = "proxy"
 main = "src/index.ts"
-compatibility_date = "2023-10-30"
+compatibility_date = "2024-05-13"
 compatibility_flags = [ "nodejs_compat" ]
 
 [env.staging]
-[env.prod]
+  # The rate limiting API is in open beta.
+  [[env.staging.unsafe.bindings]]
+  name = "API_RATE_LIMITER"
+  type = "ratelimit"
+  # An identifier you define, that is unique to your Cloudflare account.
+  # Must be an integer.
+  namespace_id = "1"
+
+  # Limit: the number of tokens allowed within a given period in a single
+  # Cloudflare location
+  # Period: the duration of the period, in seconds. Must be either 10 or 60
+  simple = { limit = 100, period = 60 }
+
+
+[env.prod]
+  # The rate limiting API is in open beta.
+  [[env.prod.unsafe.bindings]]
+  name = "API_RATE_LIMITER"
+  type = "ratelimit"
+  # An identifier you define, that is unique to your Cloudflare account.
+  # Must be an integer.
+  namespace_id = "2"
+
+  # Limit: the number of tokens allowed within a given period in a single
+  # Cloudflare location
+  # Period: the duration of the period, in seconds. Must be either 10 or 60
+  simple = { limit = 300, period = 60 }

apps/webapp/.gitignore

@@ -17,4 +17,5 @@ build-storybook.log
 .storybook-out
 storybook-static
 
-/prisma/seed.js
+/prisma/seed.js
+/prisma/populate.js

apps/webapp/app/assets/icons/AISparkleIcon.tsx

@@ -0,0 +1,53 @@
+export function AISparkleIcon({ className }: { className?: string }) {
+  return (
+    <svg className={className} viewBox="0 0 18 18" fill="none" xmlns="http://www.w3.org/2000/svg">
+      <path
+        d="M14.9806 0.803884C14.8871 0.33646 14.4767 0 14 0C13.5233 0 13.1129 0.33646 13.0194 0.803884L12.7809 1.99644C12.7017 2.3923 12.3923 2.70174 11.9964 2.78091L10.8039 3.01942C10.3365 3.1129 10 3.52332 10 4C10 4.47668 10.3365 4.8871 10.8039 4.98058L11.9964 5.21909C12.3923 5.29826 12.7017 5.6077 12.7809 6.00356L13.0194 7.19612C13.1129 7.66354 13.5233 8 14 8C14.4767 8 14.8871 7.66354 14.9806 7.19612L15.2191 6.00356C15.2983 5.6077 15.6077 5.29826 16.0036 5.21909L17.1961 4.98058C17.6635 4.8871 18 4.47668 18 4C18 3.52332 17.6635 3.1129 17.1961 3.01942L16.0036 2.78091C15.6077 2.70174 15.2983 2.3923 15.2191 1.99644L14.9806 0.803884Z"
+        fill="url(#paint0_linear_11402_36656)"
+      />
+      <path
+        d="M5.94868 4.68377C5.81257 4.27543 5.43043 4 5 4C4.56957 4 4.18743 4.27543 4.05132 4.68377L3.36754 6.73509C3.26801 7.03369 3.03369 7.26801 2.73509 7.36754L0.683772 8.05132C0.27543 8.18743 0 8.56957 0 9C0 9.43043 0.27543 9.81257 0.683772 9.94868L2.73509 10.6325C3.03369 10.732 3.26801 10.9663 3.36754 11.2649L4.05132 13.3162C4.18743 13.7246 4.56957 14 5 14C5.43043 14 5.81257 13.7246 5.94868 13.3162L6.63246 11.2649C6.73199 10.9663 6.96631 10.732 7.26491 10.6325L9.31623 9.94868C9.72457 9.81257 10 9.43043 10 9C10 8.56957 9.72457 8.18743 9.31623 8.05132L7.26491 7.36754C6.96631 7.26801 6.73199 7.03369 6.63246 6.73509L5.94868 4.68377Z"
+        fill="url(#paint1_linear_11402_36656)"
+      />
+      <path
+        d="M12.9487 12.6838C12.8126 12.2754 12.4304 12 12 12C11.5696 12 11.1874 12.2754 11.0513 12.6838L10.8675 13.2351C10.768 13.5337 10.5337 13.768 10.2351 13.8675L9.68377 14.0513C9.27543 14.1874 9 14.5696 9 15C9 15.4304 9.27543 15.8126 9.68377 15.9487L10.2351 16.1325C10.5337 16.232 10.768 16.4663 10.8675 16.7649L11.0513 17.3162C11.1874 17.7246 11.5696 18 12 18C12.4304 18 12.8126 17.7246 12.9487 17.3162L13.1325 16.7649C13.232 16.4663 13.4663 16.232 13.7649 16.1325L14.3162 15.9487C14.7246 15.8126 15 15.4304 15 15C15 14.5696 14.7246 14.1874 14.3162 14.0513L13.7649 13.8675C13.4663 13.768 13.232 13.5337 13.1325 13.2351L12.9487 12.6838Z"
+        fill="url(#paint2_linear_11402_36656)"
+      />
+      <defs>
+        <linearGradient
+          id="paint0_linear_11402_36656"
+          x1="9"
+          y1="0"
+          x2="9"
+          y2="18"
+          gradientUnits="userSpaceOnUse"
+        >
+          <stop stopColor="#E543FF" />
+          <stop offset="1" stopColor="#286399" />
+        </linearGradient>
+        <linearGradient
+          id="paint1_linear_11402_36656"
+          x1="9"
+          y1="0"
+          x2="9"
+          y2="18"
+          gradientUnits="userSpaceOnUse"
+        >
+          <stop stopColor="#E543FF" />
+          <stop offset="1" stopColor="#286399" />
+        </linearGradient>
+        <linearGradient
+          id="paint2_linear_11402_36656"
+          x1="9"
+          y1="0"
+          x2="9"
+          y2="18"
+          gradientUnits="userSpaceOnUse"
+        >
+          <stop stopColor="#E543FF" />
+          <stop offset="1" stopColor="#286399" />
+        </linearGradient>
+      </defs>
+    </svg>
+  );
+}

apps/webapp/app/assets/icons/v3.svg

@@ -0,0 +1,4 @@
+<svg width="32" height="32" viewBox="0 0 32 32" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect x="0.861435" y="0.861435" width="30.2771" height="30.2771" rx="15.1386" stroke="#D7D9DD" stroke-width="1.72287"/>
+<path d="M14.9669 12.642L11.6417 21.7732H9.8155L6.49036 12.642H8.04094L10.7286 20.2571L13.4163 12.642H14.9669ZM20.534 14.5544C21.6884 14.5716 23.0666 14.0375 23.0666 12.4525C23.0666 11.3843 22.1018 10.7124 20.534 10.7124C19.2591 10.7124 18.3632 11.3326 18.2082 12.3146L16.6576 12.2113C16.8815 10.4884 18.4838 9.26516 20.534 9.26516C22.946 9.26516 24.6345 10.5745 24.6345 12.4525C24.6345 13.8135 23.8592 14.7267 22.3775 15.1574C24.0831 15.657 25.0479 16.8286 25.0479 18.4136C25.0479 20.55 23.1872 22.0489 20.534 22.0489C18.0876 22.0489 16.313 20.6361 16.2096 18.6203L17.743 18.517C17.8808 20.0159 19.3108 20.6016 20.534 20.6016C21.9812 20.6016 23.4974 19.947 23.4974 18.293C23.4974 16.6563 21.9812 15.9499 20.534 15.9844L19.5865 16.0016V14.5371L20.534 14.5544Z" fill="white"/>
+</svg>

apps/webapp/app/components/Feedback.tsx

@@ -1,10 +1,14 @@
 import { conform, useForm } from "@conform-to/react";
 import { parse } from "@conform-to/zod";
+import { BookOpenIcon } from "@heroicons/react/20/solid";
 import { ChevronRightIcon } from "@heroicons/react/24/solid";
 import { Form, useActionData, useLocation, useNavigation } from "@remix-run/react";
 import { DiscordIcon, GitHubLightIcon } from "@trigger.dev/companyicons";
+import { ActivityIcon } from "lucide-react";
 import { ReactNode, useState } from "react";
 import { FeedbackType, feedbackTypeLabel, schema } from "~/routes/resources.feedback";
+import { cn } from "~/utils/cn";
+import { docsPath } from "~/utils/pathBuilder";
 import { Button, LinkButton } from "./primitives/Buttons";
 import { Fieldset } from "./primitives/Fieldset";
 import { FormButtons } from "./primitives/FormButtons";
@@ -13,20 +17,9 @@ import { Header1, Header2 } from "./primitives/Headers";
 import { InputGroup } from "./primitives/InputGroup";
 import { Label } from "./primitives/Label";
 import { Paragraph } from "./primitives/Paragraph";
-import {
-  Select,
-  SelectContent,
-  SelectGroup,
-  SelectItem,
-  SelectTrigger,
-  SelectValue,
-} from "./primitives/Select";
+import { Select, SelectItem } from "./primitives/Select";
 import { Sheet, SheetBody, SheetContent, SheetTrigger } from "./primitives/Sheet";
 import { TextArea } from "./primitives/TextArea";
-import { cn } from "~/utils/cn";
-import { BookOpenIcon } from "@heroicons/react/20/solid";
-import { ActivityIcon, HeartPulseIcon } from "lucide-react";
-import { docsPath } from "~/utils/pathBuilder";
 
 type FeedbackProps = {
   button: ReactNode;
@@ -78,20 +71,20 @@ export function Feedback({ button, defaultValue = "bug" }: FeedbackProps) {
             <Fieldset className="max-w-full gap-y-3">
               <input value={location.pathname} {...conform.input(path, { type: "hidden" })} />
               <InputGroup className="max-w-full">
-                <SelectGroup>
-                  <Select {...conform.input(feedbackType)} defaultValue={defaultValue}>
-                    <SelectTrigger size="medium" width="full">
-                      <SelectValue placeholder="Type" />
-                    </SelectTrigger>
-                    <SelectContent>
-                      {Object.entries(feedbackTypeLabel).map(([key, value]) => (
-                        <SelectItem key={key} value={key}>
-                          {value}
-                        </SelectItem>
-                      ))}
-                    </SelectContent>
-                  </Select>
-                </SelectGroup>
+                <Select
+                  {...conform.select(feedbackType)}
+                  variant="tertiary/medium"
+                  defaultValue={defaultValue}
+                  placeholder="Select type"
+                  text={(value) => feedbackTypeLabel[value]}
+                  dropdownIcon
+                >
+                  {Object.entries(feedbackTypeLabel).map(([name, title]) => (
+                    <SelectItem key={name} value={name}>
+                      {title}
+                    </SelectItem>
+                  ))}
+                </Select>
                 <FormError id={feedbackType.errorId}>{feedbackType.error}</FormError>
               </InputGroup>
               <InputGroup className="max-w-full">
@@ -122,14 +115,7 @@ export function Feedback({ button, defaultValue = "bug" }: FeedbackProps) {
               Docs
             </LinkButton>
             <LinkButton
-              to={docsPath("v3/introduction")}
-              variant="tertiary/medium"
-              LeadingIcon={BookOpenIcon}
-            >
-              v3 Docs (Developer preview)
-            </LinkButton>
-            <LinkButton
-              to={"https://trigger.openstatus.dev/"}
+              to={"https://status.trigger.dev/"}
               variant="tertiary/medium"
               LeadingIcon={ActivityIcon}
             >

apps/webapp/app/components/SetupCommands.tsx

@@ -206,3 +206,39 @@ export function TriggerDevStepV3() {
     </ClientTabs>
   );
 }
+
+export function TriggerLoginStepV3() {
+  return (
+    <ClientTabs defaultValue="npm">
+      <ClientTabsList>
+        <ClientTabsTrigger value={"npm"}>npm</ClientTabsTrigger>
+        <ClientTabsTrigger value={"pnpm"}>pnpm</ClientTabsTrigger>
+        <ClientTabsTrigger value={"yarn"}>yarn</ClientTabsTrigger>
+      </ClientTabsList>
+      <ClientTabsContent value={"npm"}>
+        <ClipboardField
+          variant="primary/medium"
+          iconButton
+          className="mb-4"
+          value={`npx trigger.dev@${v3PackageTag} login`}
+        />
+      </ClientTabsContent>
+      <ClientTabsContent value={"pnpm"}>
+        <ClipboardField
+          variant="primary/medium"
+          iconButton
+          className="mb-4"
+          value={`pnpm dlx trigger.dev@${v3PackageTag} login`}
+        />
+      </ClientTabsContent>
+      <ClientTabsContent value={"yarn"}>
+        <ClipboardField
+          variant="primary/medium"
+          iconButton
+          className="mb-4"
+          value={`yarn dlx trigger.dev@${v3PackageTag} login`}
+        />
+      </ClientTabsContent>
+    </ClientTabs>
+  );
+}

apps/webapp/app/components/admin/debugTooltip.tsx

@@ -0,0 +1,31 @@
+import { ShieldCheckIcon } from "@heroicons/react/20/solid";
+import {
+  Tooltip,
+  TooltipContent,
+  TooltipProvider,
+  TooltipTrigger,
+} from "~/components/primitives/Tooltip";
+import { useIsImpersonating } from "~/hooks/useOrganizations";
+import { useHasAdminAccess } from "~/hooks/useUser";
+
+export function AdminDebugTooltip({ children }: { children: React.ReactNode }) {
+  const hasAdminAccess = useHasAdminAccess();
+  const isImpersonating = useIsImpersonating();
+
+  if (!hasAdminAccess && !isImpersonating) {
+    return null;
+  }
+
+  return (
+    <TooltipProvider>
+      <Tooltip>
+        <TooltipTrigger>
+          <ShieldCheckIcon className="size-5" />
+        </TooltipTrigger>
+        <TooltipContent className="flex max-h-[90vh] items-center gap-1 overflow-y-auto">
+          {children}
+        </TooltipContent>
+      </Tooltip>
+    </TooltipProvider>
+  );
+}

apps/webapp/app/components/billing/PricingTiers.tsx

@@ -290,6 +290,7 @@ export function TierPro({
           options={concurrencyTiers.map((c) => ({ label: `Up to ${c.upto}`, value: c.code }))}
           fullWidth
           value={concurrentBracketCode}
+          variant="primary"
           onChange={(v) => setConcurrentBracketCode(v)}
         />
         <div className="py-6">