feat: native Mistral provider (OpenAI-compatible, EU-hosted)#5
Merged
Conversation
- MistralProvider: config keys mistralApiKey/mistralBaseUrl/mistralDefaultModel, capabilities TextGeneration/Vision/ToolCalling/StructuredOutput/Reasoning/Temperature (no image generation) - MistralClient: delegates chat to OpenAiChatClient against https://api.mistral.ai/v1, throws ImageGenerationNotSupportedException for generateImage - services.xml registration, config.xml card (en + de-DE) - admin component frosh-ai-provider-mistral + module import + detail-page allowlist - en-GB/de-DE snippets, MistralProviderTest (7 tests)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds Mistral as a first-class, preconfigured provider — P0 roadmap item #5. Merchants paste an API key and go (no manual endpoint setup). Mistral's API is OpenAI-compatible, so chat is delegated to the existing
OpenAiChatClientpointed at the Mistral endpoint.Why
EU data-residency wedge for the German/EU merchant base — a strong differentiator vs. the paywalled Shopware Copilot. Cheap to add (reuses OpenAI-compatible plumbing), keeps the provider-agnostic positioning.
Changes
MistralProvider(src/Provider/Mistral/MistralProvider.php): IDmistral, config keysmistralApiKey/mistralBaseUrl/mistralDefaultModel, capabilities TextGeneration / Vision / ToolCalling / StructuredOutput / Reasoning / Temperature (no image generation).MistralClient: wrapsOpenAiChatClientforchat()againsthttps://api.mistral.ai/v1;generateImage()throwsImageGenerationNotSupportedException(Mistral text models don't generate images).services.xmlregistration (frosh_ai.providertag).config.xmlcard (en + de-DE).frosh-ai-provider-mistral+ module import + detail-page allowlist entry.MistralProviderTest(7 tests): identity/descriptor, capabilities, isConfigured, getClient (success + not-configured exception), admin status.Tests
96 tests / 376 assertions, green — verified both locally and in the
frosh-ai-devcontainer (Shopware 6.7 / PHP 8.3).Notes