Ettore Di Giacinto 69115ebda6 feat(failover): switch realtime pipeline stages per call ...

A stage that names a chain is resolved on every call, so a switch keeps
the session and its conversation. Clients get localai.model.failover
events at session start and on every switch.

Assisted-by: Claude:claude-opus-5-5

2026-09-26 18:07:56 +00:00

..

distributed

fix(distributed): exclude pinned models from cluster eviction and idle scale-down

2026-09-11 23:08:26 +00:00

mock-backend

test(failover): cover retry per endpoint family and remote fail-back

2026-09-26 17:50:54 +00:00

cloud_proxy_helpers_test.go

test(failover): cover retry per endpoint family and remote fail-back

2026-09-26 17:50:54 +00:00

e2e_anthropic_test.go

fix(anthropic): do not emit empty tokens and fix SSE tool calls (#9258)

2026-04-07 00:38:21 +02:00

e2e_cloud_proxy_test.go

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

e2e_failover_test.go

fix(failover): stop judging cold local targets by their model file

2026-09-26 17:57:17 +00:00

e2e_mcp_test.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

e2e_ollama_test.go

feat(api): add ollama compatibility (#9284)

2026-04-09 14:15:14 +02:00

e2e_pii_ner_test.go

fix(pii): post-merge review fixes + live NER e2e for the privacy-filter tier (#10401)

2026-06-22 18:26:19 +02:00

e2e_router_test.go

fix(router): production-ready request router + auto-size batch for embedding/rerank (#10104)

2026-06-12 16:21:15 +02:00

e2e_suite_test.go

feat(failover): switch realtime pipeline stages per call

2026-09-26 18:07:56 +00:00

e2e_websocket_responses_test.go

fix(openresponses): support Codex WebSocket warm-up (#11608)

2026-09-11 16:54:42 +02:00

mock_backend_test.go

fix(openai): return HTTP errors for pre-stream failures and report per-slot context (#12204)

2026-09-22 17:19:58 +02:00

path_resolution_test.go

fix(backend): resolve relative draft_model paths against the models dir (#9680)

2026-05-06 00:58:38 +02:00

realtime_classifier_ws_test.go

feat(classifier/VAD): support voice control on low power devices (#10804)

2026-07-29 12:50:22 +02:00

realtime_speaker_identity_test.go

feat(realtime): speaker-aware conversations - surface identity to client and LLM (#10424)

2026-06-21 21:07:10 +02:00

realtime_voicegate_test.go

test(e2e): live-server voice-recognition gate test (#10324)

2026-06-13 23:54:27 +02:00

realtime_webrtc_test.go

feat(realtime): WebRTC support (#8790)

2026-03-13 21:37:15 +01:00

realtime_ws_test.go

feat(failover): switch realtime pipeline stages per call

2026-09-26 18:07:56 +00:00

run-realtime-sherpa.sh

feat: Add Sherpa ONNX backend for ASR and TTS (#8523)

2026-04-24 14:40:06 +02:00