Laravel AI Agents: Streaming & Structured Output | Mohamed Said [ ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MH.png) Mohamed Said Laravel Backend Engineer ](https://msaied.com) [ Home ](https://msaied.com) [ Projects ](https://msaied.com/projects) [ Articles ](https://msaied.com/articles) [ Certificates ](https://msaied.com/certificates) [ Contact ](https://msaied.com#contact-section) [ ](https://github.com/EG-Mohamed) [ Home ](https://msaied.com) [ Projects ](https://msaied.com/projects) [ Articles ](https://msaied.com/articles) [ Certificates ](https://msaied.com/certificates) [ Contact ](https://msaied.com#contact-section) [ home ](https://msaied.com) [ articles ](https://msaied.com/articles) Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts On this page 1. [ Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts ](#production-ai-agents-in-laravel-streaming-token-budgets-and-structured-output-contracts) 2. [ Streaming Responses Over SSE ](#streaming-responses-over-sse) 3. [ Enforcing Token Budgets ](#enforcing-token-budgets) 4. [ Structured Output Contracts ](#structured-output-contracts) 5. [ Putting It Together in a Job ](#putting-it-together-in-a-job) 6. [ Takeaways ](#takeaways) ![Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts](https://cdn.msaied.com/325/ee4e73c7fdfa922304594beaac92c93c.png) #laravel #ai #openai #production Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts ============================================================================================ 30 Jun 2026 4 min read ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said Table of contents 1. [ 01 Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts ](#production-ai-agents-in-laravel-streaming-token-budgets-and-structured-output-contracts) 2. [ 02 Streaming Responses Over SSE ](#streaming-responses-over-sse) 3. [ 03 Enforcing Token Budgets ](#enforcing-token-budgets) 4. [ 04 Structured Output Contracts ](#structured-output-contracts) 5. [ 05 Putting It Together in a Job ](#putting-it-together-in-a-job) 6. [ 06 Takeaways ](#takeaways) Production AI Agents in Laravel: Streaming, Token Budgets, and Structured Output Contracts ------------------------------------------------------------------------------------------ Most tutorials stop at "call the API, dump the response." Production agents are a different beast. You need to stream tokens to the browser without blocking a PHP worker for 30 seconds, enforce hard token budgets so a runaway prompt doesn't drain your quota, and guarantee that the model returns data your application can actually parse. This article covers all three. --- ### Streaming Responses Over SSE Laravel's `StreamedResponse` pairs naturally with OpenAI's streaming API. The key is flushing output incrementally without buffering the entire completion. ```php use Illuminate\Support\Facades\Route; use Symfony\Component\HttpFoundation\StreamedResponse; use OpenAI\Laravel\Facades\OpenAI; Route::get('/chat/stream', function () { return new StreamedResponse(function () { $stream = OpenAI::chat()->createStreamed([ 'model' => 'gpt-4o', 'messages' => [['role' => 'user', 'content' => request('prompt')]], ]); foreach ($stream as $response) { $delta = $response->choices[0]->delta->content ?? ''; if ($delta !== '') { echo 'data: ' . json_encode(['token' => $delta]) . "\n\n"; ob_flush(); flush(); } } echo "data: [DONE]\n\n"; }, 200, [ 'Content-Type' => 'text/event-stream', 'Cache-Control' => 'no-cache', 'X-Accel-Buffering' => 'no', // critical for nginx ]); }); ``` `X-Accel-Buffering: no` is the header most people forget. Without it, nginx will buffer the entire response before forwarding it to the client, defeating the purpose of streaming entirely. --- ### Enforcing Token Budgets Token overruns are a billing and latency problem. Enforce budgets at two layers: before the request (prompt token estimation) and inside the request (`max_tokens`). ```php final class TokenBudget { public function __construct( private readonly int $maxPromptTokens = 3_000, private readonly int $maxCompletionTokens = 1_000, ) {} public function assertPromptFits(string $prompt): void { // ~4 chars per token is a safe heuristic for English text $estimated = (int) ceil(mb_strlen($prompt) / 4); if ($estimated > $this->maxPromptTokens) { throw new \OverflowException( "Prompt exceeds budget: ~{$estimated} tokens (max {$this->maxPromptTokens})" ); } } public function completionLimit(): int { return $this->maxCompletionTokens; } } ``` Bind this as a singleton scoped to the current tenant or user plan: ```php $this->app->scoped(TokenBudget::class, function () { $plan = auth()->user()?->plan ?? 'free'; return match ($plan) { 'pro' => new TokenBudget(8_000, 2_000), default => new TokenBudget(3_000, 500), }; }); ``` Using `scoped` rather than `singleton` ensures the budget resets per request, which matters under Octane. --- ### Structured Output Contracts Asking a model to "return JSON" is not a contract. OpenAI's `response_format` with `json_schema` mode (available on `gpt-4o` and later) lets you enforce a schema server-side. Pair it with a DTO and a Pest assertion. ```php $response = OpenAI::chat()->create([ 'model' => 'gpt-4o', 'messages' => [ ['role' => 'system', 'content' => 'Extract the invoice fields.'], ['role' => 'user', 'content' => $rawText], ], 'response_format' => [ 'type' => 'json_schema', 'json_schema' => [ 'name' => 'invoice', 'strict' => true, 'schema' => [ 'type' => 'object', 'properties' => [ 'vendor' => ['type' => 'string'], 'amount' => ['type' => 'number'], 'due_date'=> ['type' => 'string', 'format' => 'date'], ], 'required' => ['vendor', 'amount', 'due_date'], 'additionalProperties' => false, ], ], ], ]); $data = json_decode($response->choices[0]->message->content, true, flags: JSON_THROW_ON_ERROR); $invoice = InvoiceData::from($data); // Spatie Data DTO ``` With `strict: true`, the model will refuse to produce output that violates the schema rather than hallucinating extra fields. Validate the DTO immediately after hydration — never trust the model's output downstream without a type check. --- ### Putting It Together in a Job For non-interactive agents, run the completion inside a queued job with a timeout that matches your token budget: ```php class ExtractInvoiceJob implements ShouldQueue { public int $timeout = 60; public int $tries = 2; public function handle(TokenBudget $budget, InvoiceExtractor $extractor): void { $budget->assertPromptFits($this->rawText); $invoice = $extractor->extract($this->rawText, $budget->completionLimit()); InvoiceExtracted::dispatch($invoice); } } ``` Set `$timeout` conservatively. A 500-token completion at peak load can still take 20+ seconds. --- ### Takeaways - Add `X-Accel-Buffering: no` to every SSE response or nginx will swallow your stream. - Use `scoped()` for per-request token budgets under Octane, not `singleton()`. - OpenAI's `json_schema` response format with `strict: true` is a real contract, not a prompt suggestion. - Validate and hydrate into a typed DTO immediately — never pass raw model output into business logic. - Set explicit job `$timeout` values that reflect your worst-case token budget, not a generic default. Found this useful? [ ](https://twitter.com/intent/tweet?url=https%3A%2F%2Fmsaied.com%2Farticles%2Fproduction-ai-agents-in-laravel-streaming-token-budgets-and-structured-output-contracts-1&text=Production+AI+Agents+in+Laravel%3A+Streaming%2C+Token+Budgets%2C+and+Structured+Output+Contracts) [ ](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fmsaied.com%2Farticles%2Fproduction-ai-agents-in-laravel-streaming-token-budgets-and-structured-output-contracts-1) Frequently Asked Questions ---------------------------- 3 questions Q01 Why does my nginx proxy buffer the SSE stream even with StreamedResponse? Nginx buffers proxy responses by default. Set the `X-Accel-Buffering: no` response header to instruct nginx to pass chunks through immediately. You may also need `proxy_buffering off` in your nginx config for non-Accel setups. Q02 Is the 4-characters-per-token heuristic accurate enough for budget enforcement? It is a safe overestimate for English prose, which is intentional. For precise counts use a tokenizer library (e.g., tiktoken via a PHP FFI binding), but the heuristic is sufficient for a pre-flight guard that errs on the side of caution. Q03 Does `json\_schema` response format work with all OpenAI models? Structured output with `strict: true` requires `gpt-4o` (2024-08-06 snapshot or later) or `gpt-4o-mini`. Earlier models support `response_format: {type: json_object}` but without schema enforcement, so the model can still produce non-conforming output. Continue reading More Articles --------------- [ View all ](https://msaied.com/articles) [ ![Laravel 13: New Features, Helpers, and Practical Upgrade Notes](https://cdn.msaied.com/339/58c4fa6fe9b6d25a2dac17c621b6f4c6.png) laravel laravel-13 upgrade ### Laravel 13: New Features, Helpers, and Practical Upgrade Notes Laravel 13 ships with async-first defaults, a leaner bootstrapping layer, and several quality-of-life helpers.... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 1 Jul 2026 3 min read Read ](https://msaied.com/articles/laravel-13-new-features-helpers-and-practical-upgrade-notes) [ ![Laravel 12: Structured Route Files, Slim Skeletons, and the New Application Bootstrapping](https://cdn.msaied.com/337/05b39d16d0f88a5fb94d0cf74049b88b.png) laravel laravel-12 upgrade ### Laravel 12: Structured Route Files, Slim Skeletons, and the New Application Bootstrapping Laravel 12 ships with a leaner skeleton, first-class route file organisation, and a revised application bootst... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 1 Jul 2026 3 min read Read ](https://msaied.com/articles/laravel-12-structured-route-files-slim-skeletons-and-the-new-application-bootstrapping) [ ![Laravel API Resources: Sparse Fieldsets, Conditional Relationships, and Versioning](https://cdn.msaied.com/336/89d518450335e8fcdaa5be882cf4dd3e.png) laravel api resources ### Laravel API Resources: Sparse Fieldsets, Conditional Relationships, and Versioning Go beyond basic API resources. Learn how to implement sparse fieldsets, conditionally load relationships, and... ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MJ.jpg) Mohamed Said 1 Jul 2026 3 min read Read ](https://msaied.com/articles/laravel-api-resources-sparse-fieldsets-conditional-relationships-and-versioning) [ ![Mohamed Said](https://cdn.msaied.com/01KT78WE565VEMM3PSNQAAB0MH.png) Mohamed Said Laravel Backend Engineer ](https://msaied.com)Senior Backend Engineer specializing in Laravel, scalable SaaS platforms, APIs, and cloud infrastructure. I build secure, high-performance web applications that help businesses grow. Explore - [Home](https://msaied.com) - [Projects](https://msaied.com/projects) - [Articles](https://msaied.com/articles) - [Certificates](https://msaied.com/certificates) - [Contact](https://msaied.com#contact-section) Connect - [ hello@msaied.com ](mailto:hello@msaied.com) - [ +20 109 461 9204 ](tel:+201094619204) © 2026 Mohamed Said. All rights reserved. [ ](https://github.com/EG-Mohamed) [ ](https://www.linkedin.com/in/msaiedm/) [ ](https://wa.me/201094619204) [ ](mailto:hello@msaied.com) [ ](https://drive.google.com/file/u/0/d/1MF20IPRJyzfy32mhEutjL5EpSls0w2Q8/view)