feat: audio surfaces (TTS + transcription), imagegen.Editor, llamaswap health probe #12

Merged
steve merged 2 commits from feat/audio-and-image-edit into main 2026-07-12 04:09:30 +00:00

2 Commits

Author SHA1 Message Date
steve 9c0ac1d60b fix: address gadfly review — filename sanitization, truncation guard, shared plumbing
CI / Tidy (pull_request) Successful in 10m2s
CI / Build & Test (pull_request) Successful in 10m24s
- Transcribe: sanitize the caller-supplied multipart filename (CR/LF
  would inject Content-Disposition headers; upload metadata is
  untrusted), always send the required model/response_format fields,
  parse MIME parameters before extension matching, and give audio/opus
  its own .opus extension.
- doRaw: a response larger than maxResponseBytes is now an error, not a
  silent truncation.
- Shared plumbing: requireBaseURL() + newRequest() helpers replace the
  7x-duplicated guard/error string and the triplicated request
  building across doJSON/doRaw/Health.
- Health: non-2xx now returns *llm.APIError (package convention,
  programmatically distinguishable from transport failure) instead of
  a one-off unexported error type.
- Speak: reject negative Speed; speechMIME no longer accepts video/*
  Content-Types.
- image.go: Generate/Edit share one sdWire validate+map helper.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj
2026-07-11 23:46:23 -04:00
steve 434d721b99 feat: audio surfaces (TTS + transcription), imagegen.Editor, llamaswap health probe
CI / Tidy (pull_request) Successful in 10m9s
CI / Build & Test (pull_request) Successful in 11m16s
Adversarial Review (Gadfly) / review (pull_request) Successful in 14m51s
- New leaf package `audio` (ADR-0017): SpeechModel/SpeechProvider and
  TranscriptionModel/TranscriptionProvider with imagegen conventions
  (zero value = backend default, functional options + Apply, bytes
  in/out, never URLs). Root re-exports added.
- imagegen.Editor (ADR-0018): optional image-to-image interface —
  EditRequest carries the generation knobs plus Init image and
  denoising Strength; separate interface so existing Models keep
  compiling.
- provider/llamaswap implements all of it: POST /v1/audio/speech (JSON,
  raw-audio response, MIME from Content-Type with format fallback),
  POST /v1/audio/transcriptions (multipart, response_format=json),
  ListVoices (GET /v1/audio/voices?model=, tolerant of string-list and
  object-list shapes), POST /sdapi/v1/img2img (txt2img wire +
  init_images/denoising_strength, shared image decode), and Health(ctx)
  (GET /health) — a cheap liveness probe for often-offline hosts.
- Hermetic httptest coverage for every new wire shape and validation
  path; README sections + support-matrix footnote updated in the same
  commit (also corrects the stale /v1/images/generations claim — the
  image path has been SDAPI since the seed fix).

First consumer: mort's llamaswap media tool cluster (status / image /
TTS / STT agent tools against the netherstorm host).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj
2026-07-11 23:24:14 -04:00