localai-org-maint-botandlocalai-org-maint-bot f7db51bdf5 feat(realtime): add shared WebRTC UDP port (#11436) ...

* feat(realtime): add shared WebRTC UDP port

Allow realtime WebRTC peer connections to reuse one configurable UDP mux, and surface listener bind failures through signaling.

Assisted-by: Codex:gpt-5

* test(realtime): keep UDP mux alive during bind check

The returned SettingEngine owns the UDP listener. Retain it through the duplicate-bind assertion so macOS cannot finalize the listener early and make the exclusivity check spuriously pass.

Assisted-by: Codex:gpt-5 [systematic-debugging]

* test(realtime): use IPv4 for UDP mux checks

Match the socket family used by the WebRTC UDP mux so macOS does not allocate an IPv6 probe that can coexist with the IPv4 listener.\n\nAssisted-by: Codex:gpt-5

---------

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

2026-08-10 17:57:58 +02:00

..

gen_inference_defaults

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087)

2026-05-30 12:04:10 +02:00

meta

feat(pii): restore request-scoped pseudonyms (#11272)

2026-08-09 22:37:13 +02:00

application_artifact_materializer_test.go

feat(modelartifacts): support bounded parallel Hugging Face file downloads (#11162)

2026-08-07 18:00:45 +02:00

application_config_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

application_config.go

feat(realtime): add shared WebRTC UDP port (#11436)

2026-08-10 17:57:58 +02:00

backend_capabilities_test.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

backend_capabilities.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

backend_hooks.go

feat(vllm): parity with llama.cpp backend (#9328)

2026-04-13 11:00:29 +02:00

chat_template_kwargs_test.go

feat: generic chat_template_kwargs (model config + per-request metadata) (#10359)

2026-06-16 12:16:34 +02:00

config_suite_test.go

dependencies(grpcio): bump to fix CI issues (#2362)

2024-05-21 14:33:47 +02:00

context_fit_internal_test.go

fix(config): cap auto-derived context to fit VRAM (#10696)

2026-07-06 12:53:45 +02:00

context_fit.go

fix(config): cap auto-derived context to fit VRAM (#10696)

2026-07-06 12:53:45 +02:00

defaults.go

fix(config): cap auto-derived context to fit VRAM (#10696)

2026-07-06 12:53:45 +02:00

disk_headroom_setting_test.go

fix(nodes): never schedule a model onto a node that cannot store it (#11054)

2026-07-23 00:03:21 +02:00

distributed_config_test.go

fix(distributed): configurable remote model-load timeout, and reap the load when it times out (#10948)

2026-07-19 12:01:48 +02:00

distributed_config.go

fix(nodes): never schedule a model onto a node that cannot store it (#11054)

2026-07-23 00:03:21 +02:00

gallery_test.go

feat(gallery): fall back to mirrors and a cached index when the primary source fails (#11389)

2026-08-06 17:56:36 +02:00

gallery.go

feat(gallery): fall back to mirrors and a cached index when the primary source fails (#11389)

2026-08-06 17:56:36 +02:00

generic_defaults_test.go

feat(config): prefix caching default + consolidate scattered defaults (#10415)

2026-06-20 22:44:44 +02:00

generic_defaults.go

feat(config): prefix caching default + consolidate scattered defaults (#10415)

2026-06-20 22:44:44 +02:00

gguf_media_marker_test.go

fix(vision): probe the media marker for pinned llama.cpp backend variants (#10955)

2026-07-19 12:46:50 +02:00

gguf_reasoning_test.go

Respect explicit reasoning config during GGUF thinking probe (#9463)

2026-04-21 21:53:10 +02:00

gguf.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

hardware_defaults_internal_test.go

fix(llama-cpp): cap single-pass embedding batch to fit VRAM (#10695)

2026-07-06 12:56:09 +02:00

hardware_defaults_test.go

fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)

2026-07-14 17:46:15 +02:00

hardware_defaults.go

fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)

2026-07-14 17:46:15 +02:00

hooks_llamacpp.go

feat(config): context_size: -1 to auto-use model's full trained context (#10752)

2026-07-09 09:03:40 +02:00

hooks_test.go

fix(vllm): apply Options[] engine flags before engine init (#11147)

2026-07-30 12:13:00 +02:00

hooks_vllm.go

fix(vllm): apply Options[] engine flags before engine init (#11147)

2026-07-30 12:13:00 +02:00

inference_defaults_test.go

feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)

2026-03-22 00:57:15 +01:00

inference_defaults.go

feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)

2026-03-22 00:57:15 +01:00

inference_defaults.json

feat: add MiniMax-M3 model support (#10837)

2026-07-20 08:26:51 +02:00

mitm_host_owners_test.go

feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)

2026-05-25 09:28:27 +02:00

model_artifact_binding_test.go

fix(model-artifacts): persist companion artifacts so remote workers get the base_model option (#11075)

2026-07-23 16:50:50 +02:00

model_artifact_binding.go

fix(model-artifacts): persist companion artifacts so remote workers get the base_model option (#11075)

2026-07-23 16:50:50 +02:00

model_artifact_companion_test.go

fix(model-artifacts): materialize longcat-video on the controller, and support companion repos (#10949)

2026-07-19 12:01:36 +02:00

model_artifact_fallback_test.go

fix(modelartifacts): treat CIFS EACCES as lock contention, not failure (#10986)

2026-07-20 22:12:39 +02:00

model_artifact_inference_test.go

fix(model-artifacts): materialize longcat-video on the controller, and support companion repos (#10949)

2026-07-19 12:01:36 +02:00

model_artifact_inference.go

fix(modelartifacts): treat CIFS EACCES as lock contention, not failure (#10986)

2026-07-20 22:12:39 +02:00

model_capabilities_test.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

model_capabilities.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

model_config_filter.go

feat: add distributed mode (#9124)

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

model_config_loader_companion_test.go

fix(model-artifacts): persist companion artifacts so remote workers get the base_model option (#11075)

2026-07-23 16:50:50 +02:00

model_config_loader_resolve_test.go

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

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

model_config_loader_test.go

feat: materialize Hugging Face model artifacts (#10825)

2026-07-15 01:09:33 +02:00

model_config_loader.go

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

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

model_config_test.go

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

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

model_config.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

model_load_budget_test.go

fix(distributed): scale the remote model-load deadline with checkpoint size (#11030)

2026-07-22 09:30:23 +02:00

model_load_budget.go

fix(distributed): scale the remote model-load deadline with checkpoint size (#11030)

2026-07-22 09:30:23 +02:00

model_test.go

fix(tests): inline model_test fixtures after tests/models_fixtures removal

2026-04-28 12:58:49 +00:00

mtp_test.go

feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)

2026-08-10 10:18:47 +02:00

mtp.go

fix(mtp): don't auto-enable self-spec MTP for draft-only assistant GGUFs (#10208)

2026-06-07 22:09:02 +02:00

parser_defaults.json

feat(vllm): parity with llama.cpp backend (#9328)

2026-04-13 11:00:29 +02:00

pipeline_streaming_test.go

feat(realtime): stream the LLM / TTS / transcription pipeline stages (#10176)

2026-06-11 08:43:12 +01:00

pipeline_turn_detection_test.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

reasoning_effort_test.go

feat: forward reasoning_effort to the backend so jinja models honor it (#10184)

2026-06-05 13:45:43 +00:00

runtime_settings_persist_test.go

refactor(settings): single declarative registry for runtime settings (fixes the #10845 bug class) (#10864)

2026-07-16 22:39:59 +02:00

runtime_settings_persist.go

refactor(settings): single declarative registry for runtime settings (fixes the #10845 bug class) (#10864)

2026-07-16 22:39:59 +02:00

runtime_settings_registry_internal_test.go

feat(modelartifacts): support bounded parallel Hugging Face file downloads (#11162)

2026-08-07 18:00:45 +02:00

runtime_settings_registry.go

feat(modelartifacts): support bounded parallel Hugging Face file downloads (#11162)

2026-08-07 18:00:45 +02:00

runtime_settings_startup_test.go

feat(gallery): default to index.localai.io with GitHub as a mirror (#11409)

2026-08-07 09:19:49 +02:00

runtime_settings_startup.go

feat(modelartifacts): support bounded parallel Hugging Face file downloads (#11162)

2026-08-07 18:00:45 +02:00

runtime_settings.go

feat(modelartifacts): support bounded parallel Hugging Face file downloads (#11162)

2026-08-07 18:00:45 +02:00

serving_defaults_test.go

fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)

2026-07-14 17:46:15 +02:00

serving_defaults.go

fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)

2026-07-14 17:46:15 +02:00

vllm_spec_test.go

feat(vllm-cpp): wire the full engine config surface through engine_args (#11159)

2026-08-06 12:10:56 +02:00

vllm_spec.go

feat(vllm-cpp): wire the full engine config surface through engine_args (#11159)

2026-08-06 12:10:56 +02:00

voice_gate_test.go

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

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