Modèles d'agents IA avec Trigger.dev

Créez des agents IA prêts pour la production avec l'exécution durable de Trigger.dev.

Sélection des modèles

Besoin de...                                    → Utiliser
─────────────────────────────────────────────────────
Traiter des éléments en parallèle               → Parallelization
Router vers différents modèles/handlers         → Routing
Enchaîner des étapes avec portes de validation → Prompt Chaining
Coordonner plusieurs tâches spécialisées        → Orchestrator-Workers
S'améliorer jusqu'au seuil de qualité           → Evaluator-Optimizer
Pause pour approbation manuelle                 → Human-in-the-Loop (waitpoints.md)
Diffuser la progression au frontend             → Realtime Streams (streaming.md)
Laisser l'LLM appeler vos tâches comme outils   → ai.tool (ai-tool.md)

Modèles principaux

1. Prompt Chaining (Séquentiel avec portes)

Enchaînez les appels LLM avec validation entre les étapes. Échouez rapidement si la sortie intermédiaire est mauvaise.

import { task } from "@trigger.dev/sdk";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

export const translateCopy = task({
  id: "translate-copy",
  run: async ({ text, targetLanguage, maxWords }) => {
    // Step 1: Generate
    const draft = await generateText({
      model: openai("gpt-4o"),
      prompt: `Write marketing copy about: ${text}`,
    });

    // Gate: Validate before continuing
    const wordCount = draft.text.split(/\s+/).length;
    if (wordCount > maxWords) {
      throw new Error(`Draft too long: ${wordCount} > ${maxWords}`);
    }

    // Step 2: Translate (only if gate passed)
    const translated = await generateText({
      model: openai("gpt-4o"),
      prompt: `Translate to ${targetLanguage}: ${draft.text}`,
    });

    return { draft: draft.text, translated: translated.text };
  },
});

2. Routing (Classifier → Dispatcher)

Utilisez un modèle bon marché pour classer, puis router vers le handler approprié.

import { task } from "@trigger.dev/sdk";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { z } from "zod";

const routingSchema = z.object({
  model: z.enum(["gpt-4o", "o1-mini"]),
  reason: z.string(),
});

export const routeQuestion = task({
  id: "route-question",
  run: async ({ question }) => {
    // Cheap classification call
    const routing = await generateText({
      model: openai("gpt-4o-mini"),
      messages: [
        {
          role: "system",
          content: `Classify question complexity. Return JSON: {"model": "gpt-4o" | "o1-mini", "reason": "..."}
          - gpt-4o: simple factual questions
          - o1-mini: complex reasoning, math, code`,
        },
        { role: "user", content: question },
      ],
    });

    const { model } = routingSchema.parse(JSON.parse(routing.text));

    // Route to selected model
    const answer = await generateText({
      model: openai(model),
      prompt: question,
    });

    return { answer: answer.text, routedTo: model };
  },
});

3. Parallelization

Exécutez les appels LLM indépendants simultanément avec batch.triggerByTaskAndWait.

import { batch, task } from "@trigger.dev/sdk";

export const analyzeContent = task({
  id: "analyze-content",
  run: async ({ text }) => {
    // All three run in parallel
    const { runs: [sentiment, summary, moderation] } = await batch.triggerByTaskAndWait([
      { task: analyzeSentiment, payload: { text } },
      { task: summarizeText, payload: { text } },
      { task: moderateContent, payload: { text } },
    ]);

    // Check moderation first
    if (moderation.ok && moderation.output.flagged) {
      return { error: "Content flagged", reason: moderation.output.reason };
    }

    return {
      sentiment: sentiment.ok ? sentiment.output : null,
      summary: summary.ok ? summary.output : null,
    };
  },
});

Voir : references/orchestration.md pour des modèles avancés

4. Orchestrator-Workers (Fan-out/Fan-in)

L'orchestrateur extrait les éléments de travail, les disperse aux workers, agrège les résultats.

import { batch, task } from "@trigger.dev/sdk";

export const factChecker = task({
  id: "fact-checker",
  run: async ({ article }) => {
    // Step 1: Extract claims (sequential - need output first)
    const { runs: [extractResult] } = await batch.triggerByTaskAndWait([
      { task: extractClaims, payload: { article } },
    ]);

    if (!extractResult.ok) throw new Error("Failed to extract claims");
    const claims = extractResult.output;

    // Step 2: Fan-out - verify all claims in parallel
    const { runs } = await batch.triggerByTaskAndWait(
      claims.map(claim => ({ task: verifyClaim, payload: claim }))
    );

    // Step 3: Fan-in - aggregate results
    const verified = runs
      .filter((r): r is typeof r & { ok: true } => r.ok)
      .map(r => r.output);

    return { claims, verifications: verified };
  },
});

5. Evaluator-Optimizer (Boucle d'auto-affinement)

Générez → Évaluez → Réessayez avec retours jusqu'à approbation.

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

export const refineTranslation = task({
  id: "refine-translation",
  run: async ({ text, targetLanguage, feedback, attempt = 0 }) => {
    // Bail condition
    if (attempt >= 5) {
      return { text, status: "MAX_ATTEMPTS", attempts: attempt };
    }

    // Generate (with feedback if retrying)
    const prompt = feedback
      ? `Improve this translation based on feedback:\n${feedback}\n\nOriginal: ${text}`
      : `Translate to ${targetLanguage}: ${text}`;

    const translation = await generateText({
      model: openai("gpt-4o"),
      prompt,
    });

    // Evaluate
    const evaluation = await generateText({
      model: openai("gpt-4o"),
      prompt: `Evaluate translation quality. Reply APPROVED or provide specific feedback:\n${translation.text}`,
    });

    if (evaluation.text.includes("APPROVED")) {
      return { text: translation.text, status: "APPROVED", attempts: attempt + 1 };
    }

    // Recursive self-call with feedback
    return refineTranslation.triggerAndWait({
      text,
      targetLanguage,
      feedback: evaluation.text,
      attempt: attempt + 1,
    }).unwrap();
  },
});

Fonctionnalités spécifiques à Trigger

Gestion des erreurs

const { runs } = await batch.triggerByTaskAndWait([...]);

// Check individual results
for (const run of runs) {
  if (run.ok) {
    console.log(run.output);  // Typed output
  } else {
    console.error(run.error);  // Error details
    console.log(run.taskIdentifier);  // Which task failed
  }
}

// Or filter by task type
const verifications = runs
  .filter((r): r is typeof r & { ok: true } =>
    r.ok && r.taskIdentifier === "verify-claim"
  )
  .map(r => r.output);

Référence rapide

// Trigger and wait for result
const result = await myTask.triggerAndWait(payload);
if (result.ok) console.log(result.output);

// Batch trigger same task
const results = await myTask.batchTriggerAndWait([
  { payload: item1 },
  { payload: item2 },
]);

// Batch trigger different tasks (typed)
const { runs } = await batch.triggerByTaskAndWait([
  { task: taskA, payload: { foo: 1 } },
  { task: taskB, payload: { bar: "x" } },
]);

// Self-recursion with unwrap
return myTask.triggerAndWait(newPayload).unwrap();