LocalAI/core/backend
Richard Palethorpe c60ed75258 feat(middleware): Model routing, PII filtering, Cloud model proxies
Add a routing middleware stack and a cloud-proxy backend.

* cloud-proxy: a Go gRPC backend that forwards OpenAI- and
  Anthropic-shaped chat requests to upstream providers, with an
  optional translate mode (OpenAI request -> Anthropic /v1/messages
  -> OpenAI response) and full tool-calling support.

* routing: admission control, content-aware model routing
  (embedding cache + classifier + rerank + Arch-Router score),
  PII detection/redaction (regex + NER) with streaming filter and
  OpenAI/Anthropic adapters, and a per-user/per-key billing recorder
  backed by GORM or in-memory storage.

* middleware: UsageMiddleware records usage via the billing recorder,
  plus admission, route-model, usage-stamp and trace middlewares.

* observability: BackendTrace ring buffer stores full request bodies
  (capped), MITM proxy emits structured trace events, and router
  classifier decisions surface at /api/router/decide.

* gallery: Arch-Router-1.5B (Q4_K_M and Q8_0).

* UI: cloud-proxy model-editor fields, classifier system-prompt and
  score-normalization config, and a Traces page rendering request
  bodies.

Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
2026-05-24 09:42:31 +01:00
..
audio_transform.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
backend_suite_test.go feat: extract output with regexes from LLMs (#3491) 2024-09-13 13:27:36 +02:00
detection.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
diarization.go feat(whisper): honor client cancellation via ggml abort_callback (#9710) 2026-05-08 01:44:47 +02:00
diarization_test.go feat(api): add /v1/audio/diarization endpoint with sherpa-onnx + vibevoice.cpp (#9654) 2026-05-05 15:10:13 +02:00
embeddings.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
face_analyze.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
face_embed.go feat(whisper): honor client cancellation via ggml abort_callback (#9710) 2026-05-08 01:44:47 +02:00
face_verify.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
image.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
llm.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
llm_probe_test.go Respect explicit reasoning config during GGUF thinking probe (#9463) 2026-04-21 21:53:10 +02:00
llm_test.go feat(autoparser): prefer chat deltas from backends when emitted (#9224) 2026-04-04 12:12:08 +02:00
options.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
options_internal_test.go feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map (#9563) 2026-04-29 00:49:28 +02:00
rerank.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
score.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
score_test.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
soundgeneration.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
stores.go feat(middleware): Model routing, PII filtering, Cloud model proxies 2026-05-24 09:42:31 +01:00
token_metrics.go feat(whisper): honor client cancellation via ggml abort_callback (#9710) 2026-05-08 01:44:47 +02:00
tokenize.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
transcript.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
tts.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
vad.go feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
video.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
voice_analyze.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
voice_embed.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00
voice_verify.go fix(traces): cap backend trace Data to keep admin UI responsive (#9960) 2026-05-23 14:50:40 +02:00