feat(client): OpenAI-compatible image generation and audio transcription - #112
Merged
Conversation
Adds provider-agnostic backends for the two well-defined public APIs that give hawk's pluggable MediaEngine / Transcriber seams a concrete default: - ImageClient: POST /v1/images/generations (b64_json or url results), returns raw bytes + provider URLs. - AudioClient: POST /v1/audio/transcriptions (multipart), returns the transcript text. Both are endpoint+credentials configurable so another provider (e.g. xAI image-gen) can replace the default without touching callers. Testable against an httptest server. Tests: 5 new cases (b64 decode, url results, 401 error, multipart form fields + transcript parse, 400 error). Full client suite green.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds provider-agnostic backends for the two well-defined public APIs that give hawk's pluggable MediaEngine / Transcriber seams a concrete default.
ImageClient— POST/v1/images/generations(OpenAI Images API), returns raw bytes (b64-decoded) + provider URLs; endpoint+credentials configurable so another provider (e.g. xAI image-gen) can replace the default without touching callers.AudioClient— POST/v1/audio/transcriptions(multipart), returns transcript text; configurable endpoint + language/prompt hints.Both testable against an httptest server; no shell, bounded timeouts, standard auth header.
Testing
5 new cases: b64 decode, url results, 401 error, multipart form fields + transcript parse, 400 error. Full client suite green.