Files
github-actions[bot] 86ef3c4979
📚 Publish docs / publish (push) Has been cancelled
🚀 Publish Trigger.dev Docker / units (push) Failing after 20s
🚀 Publish Trigger.dev Docker / typecheck (push) Failing after 20s
🚀 Publish Trigger.dev Docker / publish-webapp (push) Has been skipped
🚀 Publish Trigger.dev Docker / publish-worker (push) Has been skipped
🚀 Publish Trigger.dev Docker / publish-worker-v4 (push) Has been skipped
🚀 Publish Trigger.dev Docker / scan-webapp (push) Has been skipped
🧭 Helm Chart Release / lint-and-test (push) Has been cancelled
🧭 Helm Chart Release / release (push) Has been cancelled
🚀 Publish Trigger.dev Docker / 📣 Dispatch main image (push) Has been cancelled
chore: release v4.5.0 (#3998)
# Trigger.dev v4.5.0

4.5.0 is the GA of the AI Agents platform. Everything built during the
prerelease line (durable agents, Sessions, AI Prompts) is now stable on
the `latest` tag, alongside a set of SDK and runtime improvements.

## AI Agents (`chat.agent`)

Run Vercel AI SDK chat completions as durable Trigger.dev tasks instead
of fragile API routes. A conversation runs as one long-lived task keyed
on `chatId`, so it survives page refreshes, network blips, redeploys,
and crashes, and every turn is a span in the dashboard.

```ts
import { chat } from "@trigger.dev/sdk/ai";
import { streamText, stepCountIs } from "ai";
import { anthropic } from "@ai-sdk/anthropic";

export const myChat = chat.agent({
  id: "my-chat",
  run: async ({ messages, signal }) => {
    return streamText({
      ...chat.toStreamTextOptions(), // system prompt, compaction, steering, telemetry
      model: anthropic("claude-sonnet-4-5"),
      messages,
      abortSignal: signal,
      stopWhen: stepCountIs(15),
    });
  },
});
```

## Sessions

The durable primitive underneath `chat.agent`, usable on its own: a
run-aware, bidirectional stream channel keyed on a stable `externalId`
whose `.in` / `.out` streams survive run boundaries (suspend, crash,
idle-timeout, redeploy). One Session spans many runs, which makes it a
good fit for agent inboxes and approval flows.

```ts
import { sessions } from "@trigger.dev/sdk";

// Create the session and trigger its first run (idempotent on externalId)
await sessions.start({
  type: "inbox",
  externalId: userId,
  taskIdentifier: "inbox-agent",
});

const session = sessions.open(userId);
await session.in.send({ text: "hello" });

const stream = await session.out.read({ signal: AbortSignal.timeout(30_000) });
for await (const chunk of stream) console.log(chunk); // durable across run swaps
```

## AI Prompts

Define prompt templates as code, versioned on every deploy, and override
the text or model from the dashboard without redeploying
(environment-scoped). Each generation links back to its prompt version
for usage, cost, and latency.

```ts
import { prompts } from "@trigger.dev/sdk";
import { z } from "zod";

export const supportPrompt = prompts.define({
  id: "customer-support",
  model: "gpt-4o",
  variables: z.object({ customerName: z.string(), issue: z.string() }),
  content: `You are a support agent for Acme.
Customer: {{customerName}}
Issue: {{issue}}`,
});

// Honors any active dashboard override, else the current deployed version
const resolved = await supportPrompt.resolve({ customerName: "Alice", issue: "Can't log in" });
// resolved.text, resolved.model, resolved.version
```

## `useChat` integration

`useTriggerChatTransport` is a Vercel AI SDK `ChatTransport` that runs
`useChat` over Trigger.dev realtime with no API routes. Text, tool
calls, reasoning, and `data-*` parts stream natively, and it works with
AI SDK v5, v6, and now v7.

## First-turn fast path (`chat.headStart`)

Runs the first turn in your warm server process while the agent boots in
parallel, cutting cold-start time-to-first-chunk roughly in half
(measured ~2.8s to ~1.2s). Available via the new
`@trigger.dev/sdk/chat-server` subpath.

## Human-in-the-loop, stop, and steering

The agent control surface: tool approvals (`needsApproval` +
`addToolApprovalResponse`), client-driven stop-generation, mid-execution
steering (`pendingMessages`), and between-turn context injection
(`chat.inject` / `chat.defer`), all durable across the conversation.

## Agent Skills

`skills.define({ id, path })` bundles a `SKILL.md` folder into your
deploy image. The agent gets a one-line summary up front and loads the
full instructions plus scoped `bash` / `readFile` tools on demand
(progressive disclosure), so a capability is something the model reaches
for rather than a pre-declared typed tool.

## `trigger skills` for coding assistants

`trigger skills` installs version-pinned Trigger.dev skills plus a
bundled docs snapshot into Claude Code, Cursor, GitHub Copilot, and
Codex, so your assistant's Trigger.dev knowledge stays current with your
installed SDK version. `trigger init` now offers to set up the MCP
server and skills too.

## Model library

A new Models page in the dashboard: a catalog of models grouped by
provider with context window, capabilities, and input / output pricing
per 1M tokens, plus a "Your models" tab showing per-model usage, cost,
and cache-hit sparklines from your actual traffic.

## Dev branches

Run multiple local `trigger dev` sessions in parallel (separate git
worktrees or coding agents) without runs colliding, each isolated with
its own dashboard, via `trigger dev --branch <name>`.

## `TriggerClient`

An instantiable client so one process can trigger and read across
projects, environments, and preview branches, each with its own auth and
baseURL, with no shared global state.

```ts
import { TriggerClient } from "@trigger.dev/sdk";

const prod = new TriggerClient({ accessToken: process.env.TRIGGER_PROD_KEY });
const preview = new TriggerClient({
  accessToken: process.env.TRIGGER_PREVIEW_KEY,
  previewBranch: "signup-flow",
});

await prod.tasks.trigger("send-email", { to: "user@example.com" });
await preview.runs.list({ status: ["COMPLETED"] });
```

## SDK and runtime

- AI SDK 7 support (v5 and v6 still supported), with OpenTelemetry
telemetry auto-wired
- Large trigger-payload offload: trigger payloads at or above 128KB
upload to object storage automatically, using the same auth and baseURL
as the trigger call
- Region support on the runs API: filter runs by region and read each
run's executing region (also on MCP `list_runs`)
- Duplicate task-id detection: `dev` and `deploy` fail with a clear
error instead of silently overwriting
- `envvars.upload` gains an `isSecret` flag to import redacted secret
variables
- Retry hardening: `TASK_MIDDLEWARE_ERROR` now retries under the task's
retry policy

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-07-02 11:26:52 +01:00
..
2026-07-02 11:26:52 +01:00
2026-07-02 11:26:52 +01:00

Python Extension for Trigger.dev

The Python extension enhances Trigger.dev's build process by enabling limited support for executing Python scripts within your tasks.

Overview

This extension introduces the pythonExtension build extension, which offers several key capabilities:

  • Install Python Dependencies (Except in Dev): Automatically installs Python and specified dependencies using pip.
  • Requirements File Support: You can specify dependencies in a requirements.txt file.
  • Inline Requirements: Define dependencies directly within your trigger.config.ts file using the requirements option.
  • Virtual Environment: Creates a virtual environment (/opt/venv) inside containers to isolate Python dependencies.
  • Helper Functions: Provides a variety of functions for executing Python code:
    • run: Executes Python commands with proper environment setup.
    • runInline: Executes inline Python code directly from Node.
    • runScript: Executes standalone .py script files.
  • Custom Python Path: In development, you can configure devPythonBinaryPath to point to a custom Python installation.

Usage

  1. Add the extension to your trigger.config.ts file:
import { defineConfig } from "@trigger.dev/sdk/v3";
import { pythonExtension } from "@trigger.dev/python/extension";

export default defineConfig({
  project: "<project ref>",
  build: {
    extensions: [
      pythonExtension({
        requirementsFile: "./requirements.txt", // Optional: Path to your requirements file
        devPythonBinaryPath: ".venv/bin/python", // Optional: Custom Python binary path
        scripts: ["src/python/**/*.py"], // Glob pattern for Python scripts
      }),
    ],
  },
});
  1. (Optional) Create a requirements.txt file in your project root with the necessary Python dependencies.
pandas==1.3.3
numpy==1.21.2
import { defineConfig } from "@trigger.dev/sdk/v3";
import { pythonExtension } from "@trigger.dev/python/extension";

export default defineConfig({
  project: "<project ref>",
  build: {
    extensions: [
      pythonExtension({
        requirementsFile: "./requirements.txt",
      }),
    ],
  },
});
  1. Execute Python scripts within your tasks using one of the provided functions:

Running a Python Script

import { task } from "@trigger.dev/sdk/v3";
import { python } from "@trigger.dev/python";

export const myScript = task({
  id: "my-python-script",
  run: async () => {
    const result = await python.runScript("my_script.py", ["hello", "world"]);
    return result.stdout;
  },
});

export const myStreamingScript = task({
  id: "my-streaming-python-script",
  run: async () => {
    // You can also stream the output of the script
    const result = python.stream.runScript("my_script.py", ["hello", "world"]);

    // result is an async iterable/readable stream
    for await (const chunk of streamingResult) {
      logger.debug("convert-url-to-markdown", {
        url: payload.url,
        chunk,
      });
    }
  },
});

Running Inline Python Code

import { task } from "@trigger.dev/sdk/v3";
import { python } from "@trigger.dev/python";

export const myTask = task({
  id: "to_datetime-task",
  run: async () => {
    const result = await python.runInline(`
import pandas as pd

pd.to_datetime("${+new Date() / 1000}")
`);
    return result.stdout;
  },
});

Running Lower-Level Commands

import { task } from "@trigger.dev/sdk/v3";
import { python } from "@trigger.dev/python";

export const pythonVersionTask = task({
  id: "python-version-task",
  run: async () => {
    const result = await python.run(["--version"]);
    return result.stdout; // Expected output: Python 3.12.8
  },
});

Limitations

  • This is a partial implementation and does not provide full Python support as an execution runtime for tasks.
  • Manual intervention may be required for installing and configuring binary dependencies in development environments.

Additional Information

For more detailed documentation, visit the official docs at Trigger.dev Documentation.