mudler's LocalAI [bot] 05ff401de8 fix(test): stop the backend-trace specs racing the lossy trace channel (#11146) ...

RecordBackendTrace does a non-blocking send onto a 100-slot channel and
drops when it is full, so tracing never stalls inference. The payload
bounding specs pushed all 200 traces in one tight loop, which overruns
that channel on a loaded machine: entries are dropped for good and the
Eventually waiting for 200 can never be satisfied, no matter the timeout.
CI hit this on master at 0a8a7fbb, settling at 158/200.

Feed the traces in chunks of 50, draining after each, so the channel is
never overrun and the count stays exact. Reproduced with 60 busy loops on
a 20-core box at GOMAXPROCS=2: 0/12 runs passed before, 12/12 after.


Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

2026-07-27 22:38:23 +02:00

..

agent_collections_param_test.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

agent_collections.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

agent_jobs.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

agent_responses.go

feat: add distributed mode (#9124)

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

agent_skills.go

feat: add distributed mode (#9124)

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

agents_isolation_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

agents.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

aliases_test.go

feat(models): model aliases - redirect a model name to another configured model (#10414)

2026-06-20 22:38:42 +02:00

aliases.go

feat(models): model aliases - redirect a model name to another configured model (#10414)

2026-06-20 22:38:42 +02:00

api_instructions_test.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

api_instructions.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

audio_transform.go

fix(audio-transform): serialize WebSocket writes to avoid concurrent-write panic (#10857)

2026-07-16 16:25:31 +01:00

audio.go

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

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

backend_apply_test.go

fix(backends): make backend install ops idempotent unless forced (#10643)

2026-07-02 19:16:29 +02:00

backend_available_cluster_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

backend_load_test.go

feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)

2026-07-03 18:00:37 +02:00

backend_load.go

feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)

2026-07-03 18:00:37 +02:00

backend_logs_test.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

backend_logs.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

backend_monitor.go

fix(worker): reap deleted backends and stop models that live on a worker (#10956)

2026-07-20 01:09:22 +02:00

backend_test.go

feat(backend): add magpie-tts-cpp text-to-speech backend (#11115)

2026-07-25 08:38:48 +02:00

backend.go

feat(backend): add magpie-tts-cpp text-to-speech backend (#11115)

2026-07-25 08:38:48 +02:00

branding_endpoints_test.go

test: add Go + React UI coverage gates and fill test gaps (#9989)

2026-05-26 22:06:10 +02:00

branding_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

branding.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

config_meta_test.go

fix(distributed): broadcast admin model-config changes across replicas (#10540)

2026-06-27 01:36:57 +02:00

config_meta.go

fix(distributed): broadcast admin model-config changes across replicas (#10540)

2026-06-27 01:36:57 +02:00

cors_proxy_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

cors_proxy.go

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

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

depth.go

feat(backend): add depth-anything (Depth Anything 3) C++/ggml backend + gallery (#10352)

2026-06-16 16:28:28 +02:00

detection.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

discovery_cluster_capabilities_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

discovery_cluster_installed_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

edit_model_test.go

fix(distributed): broadcast admin model-config changes across replicas (#10540)

2026-06-27 01:36:57 +02:00

edit_model.go

fix(distributed): broadcast admin model-config changes across replicas (#10540)

2026-06-27 01:36:57 +02:00

face_analyze.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_embed.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_forget.go

feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)

2026-04-22 21:55:41 +02:00

face_identify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_register.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_verify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

finetune.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

gallery.go

fix(galleryop): make admitted operations queryable and survive a failed op (#11044)

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

get_token_metrics.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

images.go

feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)

2026-04-22 21:55:41 +02:00

import_model_test.go

feat(importer): expand importer flow to almost all backends (#9466)

2026-04-22 22:42:37 +02:00

import_model.go

fix(galleryop): make admitted operations queryable and survive a failed op (#11044)

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

localai_suite_test.go

feat(webui): add import/edit model page (#6050)

2025-08-14 23:48:09 +02:00

mcp_prompts.go

feat(ui): MCP Apps, mcp streaming and client-side support (#8947)

2026-03-11 07:30:49 +01:00

mcp_resources.go

feat(ui): MCP Apps, mcp streaming and client-side support (#8947)

2026-03-11 07:30:49 +01:00

mcp_tools.go

feat: add distributed mode (#9124)

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

mcp.go

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

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

metrics.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

nodes_backends_list_test.go

fix(distributed): return empty backend list for agent nodes instead of failing backend.list (#10545) (#10565)

2026-06-28 01:22:48 +02:00

nodes_install_async_test.go

fix(distributed): make per-node backend upgrade actually upgrade (#10838)

2026-07-15 09:16:55 +02:00

nodes_scheduling_test.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

nodes_scheduling_validation_test.go

feat: prefix-cache-aware routing for distributed mode (#10071)

2026-05-30 23:24:22 +02:00

nodes_test.go

feat(ui): restructure Cluster Nodes view (pulse + panel roster + detail page) (#10447)

2026-06-22 18:24:29 +02:00

nodes_vrambudget_test.go

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

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

nodes.go

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

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

p2p.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

pii_test.go

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

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

pii.go

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

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

pin_model.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

quantization.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

router_decide_test.go

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

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

router_decide.go

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

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

score.go

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

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

settings_test.go

fix(pii): load default detectors at startup + add LOCALAI_PII_DEFAULT_DETECTORS (#10474)

2026-06-24 11:08:57 +02:00

settings.go

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

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

stores.go

feat(loader): enhance single active backend to support LRU eviction (#7535)

2025-12-12 12:28:38 +01:00

system.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

toggle_model.go

fix(distributed): broadcast admin model-config changes across replicas (#10540)

2026-06-27 01:36:57 +02:00

tokenize.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

traces_test.go

fix(test): stop the backend-trace specs racing the lossy trace channel (#11146)

2026-07-27 22:38:23 +02:00

traces.go

perf(http): gzip responses, cache hashed assets, bound the trace endpoints (#11056)

2026-07-22 22:51:25 +02:00

tts_speed_test.go

fix(tts): forward the OpenAI speed field to the backend (#11097) (#11120)

2026-07-27 19:03:32 +02:00

tts_speed.go

fix(tts): forward the OpenAI speed field to the backend (#11097) (#11120)

2026-07-27 19:03:32 +02:00

tts.go

fix(tts): forward the OpenAI speed field to the backend (#11097) (#11120)

2026-07-27 19:03:32 +02:00

types.go

feat: add distributed mode (#9124)

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

vad.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

video_internal_test.go

feat(backends): add LongCat video and avatar generation (#10792)

2026-07-12 23:58:46 +02:00

video.go

feat(backends): add LongCat video and avatar generation (#10792)

2026-07-12 23:58:46 +02:00

voice_analyze.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_embed.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_forget.go

feat: voice recognition (#9500)

2026-04-23 12:07:14 +02:00

voice_identify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_profiles_test.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

voice_profiles.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

voice_register.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_verify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

vram_test.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

vram.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

welcome.go

feat: add distributed mode (#9124)

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