trypost/tests/Unit/Services/Ai/AiImageClientTest.php

221 lines
7.1 KiB
PHP
Raw Permalink Normal View History

feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
<?php
declare(strict_types=1);
use App\Enums\Workspace\ImageStyle;
use App\Services\Ai\AiImageClient;
Fix OpenRouter via laravel/ai default provider (revises #216) (#220) * Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-08-11 00:38:50 +00:00
use Illuminate\Support\Collection;
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
use Laravel\Ai\Image;
use Laravel\Ai\Prompts\ImagePrompt;
Fix OpenRouter via laravel/ai default provider (revises #216) (#220) * Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-08-11 00:38:50 +00:00
use Laravel\Ai\Responses\Data\Meta;
use Laravel\Ai\Responses\Data\Usage;
use Laravel\Ai\Responses\ImageResponse;
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
test('generate returns null when keywords are empty', function () {
Image::fake();
$client = new AiImageClient;
expect($client->generate([], ImageStyle::Cinematic))->toBeNull();
Image::assertNothingGenerated();
});
Fix OpenRouter via laravel/ai default provider (revises #216) (#220) * Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-08-11 00:38:50 +00:00
test('generate returns bytes plus the resolved provider and model when AI succeeds', function () {
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
$bytes = base64_decode('iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==');
Image::fake([base64_encode($bytes)]);
$client = new AiImageClient;
Fix OpenRouter via laravel/ai default provider (revises #216) (#220) * Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-08-11 00:38:50 +00:00
$result = $client->generate(['kitchen', 'morning'], ImageStyle::Illustration);
expect($result)
->not->toBeNull()
->and($result['bytes'])->toBe($bytes)
->and($result['provider'])->toBe('openai')
->and($result['model'])->toBe('gpt-image-2');
});
test('generate honours AI_IMAGE_PROVIDER instead of always using OpenAI', function () {
config()->set('ai.default_for_images', 'gemini');
Image::fake();
$client = new AiImageClient;
$result = $client->generate(['kitchen'], ImageStyle::Illustration);
expect($result)
->not->toBeNull()
->and($result['provider'])->toBe('gemini');
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
});
test('generate uses style-specific prompt prefix', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['mountain hiker'], ImageStyle::Cinematic);
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Cinematic photograph')
&& $prompt->contains('mountain hiker'));
});
test('generate maps orientation to portrait', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, orientation: 'portrait');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->isPortrait());
});
test('generate maps orientation to landscape', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, orientation: 'landscape');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->isLandscape());
});
test('generate falls back to square for unknown orientation', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, orientation: 'whatever');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->isSquare());
});
test('generate appends Brazilian Portuguese instruction when language is pt-BR', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, language: 'pt-BR');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Brazilian Portuguese'));
});
test('generate appends Spanish instruction when language is es', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, language: 'es');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Spanish'));
});
test('generate appends French instruction when language is fr', function () {
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, language: 'fr');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('French'));
});
Add Ukrainian as a supported platform language (#219) * Default AI content language to Ukrainian * Keep English as the default content language * refactor: update content language handling in workspace creation - Changed the default content language in CreateWorkspace to inherit the app's locale instead of defaulting to English. - Updated related tests to reflect this change, ensuring that the content language aligns with the application's current locale settings. - Cleaned up unnecessary code in the BrandTab component for better readability. * Add Ukrainian as a full platform UI locale. Wire uk into languages config with complete lang/uk translations and restore ContentLanguage↔UI parity checks. Co-authored-by: Cursor <cursoragent@cursor.com> * Wire Ukrainian into dayjs and locale coverage tests. Import the uk dayjs locale with Monday week-start and cover uk/uk-UA in brand autofill and SetLocale assertions. Co-authored-by: Cursor <cursoragent@cursor.com> * Harden Ukrainian UI and AI content-language coverage. Cover generator/reviewer/humanizer/image prompts, workspace pickers, persona labels, UI locale switch, and README for uk as a first-class platform language. Co-authored-by: Cursor <cursoragent@cursor.com> * Add Ukrainian Pinterest form strings after main merge. Restore lang/uk posts.php key parity for the new pin title and destination link fields. Co-authored-by: Cursor <cursoragent@cursor.com> * List every supported UI language in the README. Replace the abbreviated multi-language blurb with the full locale set from config. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Paulo Castellano <paulo@castellanos.llc> Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-05 22:45:30 +00:00
test('generate appends Ukrainian instruction when language is uk', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, language: 'uk');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Ukrainian'));
});
test('generate defaults to English instruction when language is unsupported', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, language: 'sv');
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('English'));
});
test('generate appends brand palette when workspace colours are provided', function () {
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::fake();
$client = new AiImageClient;
$client->generate(
['x'],
ImageStyle::Infographic,
brandColor: '#facc15',
backgroundColor: '#ffffff',
textColor: '#0f172a',
);
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('BRAND COLOR PALETTE')
&& $prompt->contains('golden yellow')
&& $prompt->contains('charts, bars')
&& $prompt->contains('off-white')
&& $prompt->contains('in-scene typography'));
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
});
test('generate omits brand palette when no workspace colours are set', function () {
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic);
Image::assertGenerated(fn (ImagePrompt $prompt) => ! $prompt->contains('BRAND COLOR PALETTE'));
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
});
test('generate includes only valid colours in the palette', function () {
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, brandColor: 'not-a-hex', backgroundColor: '#ffffff');
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('BRAND COLOR PALETTE')
&& $prompt->contains('off-white')
&& ! $prompt->contains('Brand / primary accent'));
feat: AI image generation pipeline and post creation overhaul Core changes: - Replace Unsplash slide pipeline with gpt-image-2 via Laravel AI SDK. New AiImageClient builds prompts from a Blade template seeded by the workspace's ImageStyle enum, content language, brand color (mapped to a human-readable name via HexColorName helper) and brand description. - Drop Template B from TemplateImageGenerator: every slide now renders as Template A (full-bleed photo + bottom gradient + white/grey overlay). Removes renderTemplateB, roundCorners, blendHex, ensureContrast and the closing-slide pipeline. - StreamPostCreation creates the Post directly and dispatches PostCreationReady with post_id; the wizard kills its preview step and redirects straight to the post editor on completion. Finalize endpoint removed. - New Workspace.image_style enum field with an 8-option visual picker shared by /workspaces/create and /settings/workspace/brand via a single BrandForm component (autofill is a prop). 8 sample webp thumbs ship under public/images/branding/image-styles/. - Media items gain optional source ('ai'|'unsplash'|'giphy') and source_meta (recipe needed to regenerate AI images later); the gallery picker tags Unsplash/Giphy attachments. - Brand-color autofill: new CssColorFrequencyExtractor parses every hex/rgb/hsl value in the homepage CSS, clusters perceptually similar shades in CIE LAB (Delta E 76 < 12), filters neutrals and returns the most frequent cluster. Solves Tailwind/utility-CSS sites where no semantic --primary variable is exposed. - Credits: gpt-image-2 metered at 15 credits/image (low quality default). - Layout: AuthSplitLayout right column is sticky/h-svh so the form textarea growth no longer stretches the marketing slider. - i18n cleanup: localized labels follow the no-em-dash convention.
2026-05-08 16:38:30 +00:00
});
test('generate appends brand context when brandDescription is provided', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, brandDescription: 'a fitness coaching brand for busy professionals');
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Brand context')
&& $prompt->contains('fitness coaching'));
});
test('generate truncates brand description longer than 200 chars', function () {
Image::fake();
$longDescription = str_repeat('lorem ipsum ', 50);
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, brandDescription: $longDescription);
Image::assertGenerated(fn (ImagePrompt $prompt) => $prompt->contains('Brand context')
&& $prompt->contains('…'));
});
test('generate omits brand context when brandDescription is empty or whitespace', function () {
Image::fake();
$client = new AiImageClient;
$client->generate(['x'], ImageStyle::Cinematic, brandDescription: ' ');
Image::assertGenerated(fn (ImagePrompt $prompt) => ! $prompt->contains('Brand context'));
});
test('generate returns null when SDK throws', function () {
Image::fake(fn () => throw new RuntimeException('boom'));
$client = new AiImageClient;
expect($client->generate(['x'], ImageStyle::Cinematic))->toBeNull();
});
Fix OpenRouter via laravel/ai default provider (revises #216) (#220) * Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-08-11 00:38:50 +00:00
test('generate returns null instead of throwing when the provider responds with no images', function () {
Image::fake(fn () => new ImageResponse(
new Collection,
new Usage,
new Meta('openai', 'gpt-image-2'),
));
$client = new AiImageClient;
expect($client->generate(['x'], ImageStyle::Cinematic))->toBeNull();
});