* 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>
* fix: subscribe to AI generation channel before dispatching the job
AiGenerateDialog posted the generate request and only subscribed to the
broadcast channel once the response came back. Reverb's plain Channel
(vendor/laravel/reverb/.../Channels/Channel.php) delivers broadcasts by
iterating the in-memory connection list at send time only — no history,
no replay. If the queued job started streaming text_delta/stream_end
events before the private-channel subscribe handshake finished, those
events were gone for good and the dialog hung on 'streaming' forever.
Generate the generation_id client-side, await channel subscription
confirmation (Echo's channel.subscribed(), backed by
pusher:subscription_succeeded) before sending the generate request, and
have the backend use the client-supplied id instead of minting its own.
Related to #218.
* fix: handle subscribe failure, dialog-close race, and i18n hardcoded strings
Code review on the previous commit surfaced real gaps:
- useAiStream only handled the subscribe-success path (.subscribed()).
A definitive pusher:subscription_error (expired session, CSRF
mismatch) fell through to the 5s timeout and was treated as success,
reproducing the exact #218 hang via a different trigger. subscribe()
now returns a boolean: true on confirm-or-ambiguous-timeout (proceed
optimistically), false only on an explicit error (don't dispatch work
nothing will ever hear).
- AiGenerateDialog now bails without dispatching if the dialog is
closed while awaiting subscription confirmation (up to 5s), and
unsubscribes on a post-subscribe dispatch failure so stale listeners
can't flip status to 'completed' after an error was already shown.
- Extracted aiGenerationChannel() so the frontend has one place to
update if the channel format changes, and cross-referenced the two
remaining backend copies (PostAiGenerateController, StreamPostContent).
- Replaced the two hardcoded English fallback error strings with i18n
keys (posts.ai.generate.errors.*) across all 16 locales — this app
only ships translated copy.
- Simplified subscribe(): dropped a redundant "already settled" guard
and the clearTimeout bookkeeping — Promise.resolve() already no-ops
after the first call, so there was nothing to guard.
* fix: subscribe before dispatch in AI post creation and image regeneration flows
Extracts subscribePrivateChannel as a shared helper and applies the same
subscribe-before-dispatch fix from the post edit flow (issue #218) to the
other two flows that stream over private channels.
Post creation wizard moves the StreamPostCreation dispatch out of
AiPostWizard.vue and into Loading.vue, so the channel is subscribed before
the job that broadcasts on it is dispatched — previously a full page
navigation happened between dispatch and subscribe with no timeout
fallback, so a lost event hung the page forever.
* refactor: trim explanatory comments added in the subscribe-before-dispatch fix
Rationale lives in the commit history, not scattered inline comments.
* refactor: trim remaining explanatory comments from the subscribe-before-dispatch fix
Same cleanup as the previous commit, applied to the files from the
original post-edit-flow fix.
* fix: dedup post-creation dispatch, surface field-level AI errors, harden edge cases
Uses ShouldBeUnique on StreamPostCreation (scoped per-user) instead of an
ad-hoc cache guard, matching the pattern already used by
PublishToSocialPlatform and VerifyUpcomingPostConnections.
Field-level validation errors (prompt/instruction) now render inline via
InputError, matching how every other form in the app surfaces them, instead
of a generic status banner. Also fixes a 422 response missing the `errors`
key that Inertia's client silently swallows, adds error handling around the
wizard's navigation to the loading page, and extracts the duplicated
error-message parsing into a shared helper.
Persist whether a post was created through web, MCP, API, or automation so we can attribute entry points without guessing from request context.
Co-authored-by: Cursor <cursoragent@cursor.com>
The image pipeline already threads `applyBrandVisuals` through
`TemplateContext` -> `PostImagePipeline` -> `TemplateImageGenerator`, but it was
hardcoded to `true` at the dispatch site, so generated images always used the
workspace brand palette with no way to opt out.
Expose the choice in the create wizard: a "Brand colors" / "Let AI decide"
toggle (shown only when images are generated). The flag flows
front -> `StartPostCreationRequest` (`apply_brand_visuals`) ->
`PostAiCreateController@start` -> `StreamPostCreation` -> `TemplateContext`,
defaulting to `true` so existing behavior is unchanged when the field is absent.
Replace the 'single'/'carousel' string format threaded through the AI
generation path with a typed GeneratorFormat enum (PostContentGenerator,
PostContentHumanizer, PostContentStreamer, StreamPostCreation,
RunGenerateNode, deriveFormat).
Remove generatorFormat() from AiContentTemplate and the three templates —
it conflated style and format (returning 'tweet_card'). The tweet-card
check now lives on ContentStyle via isTweetCard(), and the humanizer skip
on ContentStyle::humanizes(), so the style declares its own behaviour
instead of callers comparing magic strings.
The humanize() guard was keyed on format string 'tweet_card', but for tweet_card
carousel the format becomes 'carousel'. Changed the guard to key on the style key
($this->template === 'tweet_card') so humanization is skipped for all tweet_card
variants — single and carousel alike.
- TemplateContext gains bool $isCarousel (set from format === CAROUSEL_FORMAT in StreamPostCreation)
- AiContentTemplate interface: promptView() now takes TemplateContext
- ImageCardTemplate handles both single and carousel via context.isCarousel; schema() returns the correct shape per mode; assemble() routes to assembleSingle/assembleCarousel
- TweetCardTemplate handles both single and carousel; promptView() returns tweet_card_carousel view when isCarousel; schema() returns {tweet_text} or {caption, slides[]}; assemble() calls forTweetCard (single) or forTweetCardCarousel (carousel)
- CarouselTemplate deleted — carousel is now a format dimension each style handles, not a standalone style
- AiTemplateRegistry: [ImageCardTemplate, TweetCardTemplate] only
- PostImagePipeline: adds forTweetCardCarousel — renders one renderTweetCard per slide text, returns N media items
- StreamPostCreation: carousel detection restored to $format === CAROUSEL_FORMAT (like main); style dispatched via AiTemplateRegistry::find($this->template); humanize skips tweet_card (single and carousel)
- PostContentGenerator: promptView() call updated to pass templateContext
- New prompt: resources/views/prompts/post_content/tweet_card_carousel.blade.php
- Tests: TemplateContractTest and TweetCardTemplateTest updated for promptView(context) signature; AiTemplateRegistryTest asserts [image_card, tweet_card]; StreamPostCreationTest adds tweet_card carousel test; TweetCardTemplateTest covers both schema shapes and both promptView return values
- Add AiTemplateRegistry (resolves, keys, default)
- Add template/templateContext params to PostContentGenerator; schema() delegates to template when both are set; instructions() uses template.promptView()
- Refactor StreamPostCreation.handle() to resolve template via registry, build TemplateContext, delegate assemble() to template; add createPostFromGenerated()
- Remove handleSingle(), handleCarousel(), resolvedContentType() (no other callers)
- PostAiCreateController passes template param from request (default image_card)
- All existing AI tests green; registry test added
Replace free-text brand_tone/brand_voice_notes with a single structured
brand_voice_traits JSON column backed by the BrandVoiceTrait enum, exposed
as choice-chip pills in the brand settings UI and autofillable from a site.
Brand voice and visuals become per-automation toggles on the Generate node.
Unify the image controls into one 0-10 picker (0 = text-only, 1 = single,
2+ = carousel) and feed the generator the most restrictive selected network
so copy fits every platform. Pass that same platform context through the
humanizer pass — extracted into a shared ResolvesPlatformCopyBudget trait —
so the rewrite can no longer drift past the character cap the generator
respected, in both the automation and manual creation flows.
Persist the trigger node's schedule editor fields on save (they were
silently dropped by validated() for lacking validation rules).
Generation
- Generate node now produces the full post (text + AI image + carousel)
via a shared PostImagePipeline extracted from StreamPostCreation
- Generate config UI mirrors the /posts/create wizard (carousel slide
count, include-image toggle); drop the decorative format/unsplash keys
Flow correctness
- RSS/HTTP nodes expose named has-items (default) and no-items output
handles, labeled and colored like the Condition node
- AdvanceAutomationRun records a no_matching_edge terminal instead of
completing silently; "0 new items" feedback in the test panel
- Manual/test runs no longer persist the production dedup watermark
Run reliability
- Pause truly halts in-flight runs (production only; manual test runs
always run regardless of automation status)
- ProcessAutomationNode::failed() marks the run failed
- automation:recover-stuck-runs and automation:prune-dry-runs commands
Webhook / HTTP
- Branded User-Agent (config-driven) on outbound webhook + http_request
- Webhook fails on invalid JSON instead of silently sending {}
- HTTP custom headers editor; CodeMirror-based CodeEditor for JSON
Editor UX
- Header Test button only opens the panel; the panel has a Run button
(saves first) and owns the with-real-data toggle
- Clicking a node closes the test panel and opens its config
- Node cards: max-width + truncate so long URLs don't grow the node
Instagram carousels were stored as content_type=instagram_carousel, which the
publisher's match() did not handle — publishing failed with "Unsupported
Instagram content type: instagram_carousel" for any post created via API, MCP,
or template (the AI flow worked only thanks to an inline band-aid that rewrote
carousel to feed before saving).
A carousel is just an Instagram feed post with multiple images: the editor,
preview, and publisher already treat a multi-image feed as a carousel. So
instagram_carousel is a generation format, not a stored content type. Remove it
from the ContentType enum entirely; it now lives only as an AI generation-format
string (wizard card + slide structure + carousel templates are untouched), and
posts always persist as instagram_feed.
- ContentType: drop the InstagramCarousel case; InstagramFeed maxMediaCount 1 -> 10
- StreamPostCreation: resolvedContentType() maps carousel -> feed; band-aid removed
- StartPostCreationRequest: accept instagram_carousel as a generation format
- Frontend: carousel becomes a wizard-local AiFormat; UI/UX unchanged
- API/MCP now reject instagram_carousel as a content_type (Rule::in no longer lists it)
- TemplateImageGenerator->render() now returns a typed array shape
{path: string, source_meta: array} instead of a one-off RenderedSlide
DTO. Single internal callsite, no need for a dedicated class.
- Drop the `?? 'en'` fallback on $workspace->content_language in 6
callsites: the column has a NOT NULL default of 'en' at the DB level,
so the null coalesce was dead code.
- WorkspaceFactory now seeds content_language, brand_tone, brand_font
and image_style explicitly so make() (no DB persist) produces a
complete model — DB defaults aren't applied until create().
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.
