mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 09:08:54 -04:00
773cae7259cbd422f3fc368e5ecfd6ecebf899bf
171
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 mudler-agentandEttore Di Giacinto
|
dce91ba7aa |
fix(backends): prefer installed development builds (#12782)
* fix(ci): capture and surface ginkgo errors in run-coverage.sh The coverage script ran ginkgo per test root with `|| fail=1`, which swallowed the exit code. Combined with `make --output-sync=target`, which buffers all output and flushes at the end, the actual ginkgo error was invisible in interleaved CI logs. Every test suite passed but the script still exited 1, and the error message was buried in 22 000 lines of buffered output. Each ginkgo invocation now captures combined stdout+stderr to a per-root log file. On failure the last 80 lines are printed to stderr so the error is visible in the CI log. On success the log is replayed to stdout so test output remains visible. The build flags (--tags, --coverpkg) are quoted correctly so values containing spaces (e.g. --tags="debug auth") are preserved through eval. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ci): create output dir before writing ginkgo logs The previous commit added per-root log files but forgot to create the output directory before the first ginkgo invocation. On CI the coverage/ dir did not exist yet, so the shell redirect to cover-pkg.out.log failed with "No such file or directory" before ginkgo even ran. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(core/http): add canvas preview route to auth coverage allowlist Commit |
||
|
mudler-agentandEttore Di Giacinto
|
39b3b31153 |
fix(backends): flag a llama-cpp backend that predates native decisions (#12733)
A decision request (/v1/systemone, /v1/decisions) sends Score with question_type "systemone". A backend built before native decisions ignores that field and runs plain scoring, so the caller saw "Score was not enabled" (500) or "candidates must be non-empty" (400). The gallery "latest" image can lag behind the server, and the upgrade check compares only tag, version and digest, so /backends/upgrades did not list the backend. Recognise those two errors for a decision request, return 501 with a message that says the backend is older than the server and must be upgraded, and mark the backend stale. The upgrade check now reports a marked backend with a `reason`, and refreshes at once. Reinstalling the backend drops the mark; if the new image is still old, the next request marks it again. Model loading is not affected. Refreshing the "latest" backend image is a separate publishing step and is not part of this change. Refs #12693 Assisted-by: Claude Code:claude-sonnet-5-5 [go vet] [go test] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Richard Palethorpe
|
3de91d48d9 |
feat(motion): add GEM-X backend and duplex streaming API
Add the GEM-X native backend with live pose and root displacement output, bounded duplex WebSocket streaming, session authorization, metrics and usage accounting. Share the embedded bidirectional RPC channel adapter across streaming backends.
Include backend build and gallery integration, API documentation, schemas and tests.
Assisted-by: Codex:gpt-6
Signed-off-by: Richard Palethorpe <io@richiejp.com>
(cherry picked from commit
|
||
|
Plamen K. Kosseff
|
addcec0c28 |
fix(models): resolver-gated queueing and editor polling for manual imports
Review round at |
||
|
mudler-agentandEttore Di Giacinto
|
0177e4988c |
feat(images): add ESRGAN upscaling and Studio workflow (#12620)
* feat(images): add upscale model capabilities * fix(config): keep SD GGML upscale opt-in * feat(stablediffusion): add lazy ESRGAN upscale bridge Keep native image ownership in C++ and serialize context creation, inference and teardown. Use upscale_scale in backend options as the explicit upscale-only marker because ModelOptions does not carry usecases. Assisted-by: Codex:gpt-5 * fix(stablediffusion): validate ESRGAN settings * fix(upscale): forward typed settings and contain resolved model paths Typed settings replace legacy options without duplicates. Resolve model and trusted root symlinks before caching the model path, rejecting missing files and escapes. Assisted-by: Codex:gpt-5 * fix(upscale): validate scale and clean failed HTTP outputs Require an explicit scale bounded to 1-16, check backend results, and keep destination cleanup owned by the allocating endpoint. Cover validation, result failures, cleanup, and successful URL responses. Assisted-by: Codex:gpt-5 * feat(studio): add inline image upscale workflow Assisted-by: OpenAI:gpt-5 * test(studio): serve upscale capability fixtures * fix(stablediffusion): default ESRGAN tiling to full frame * feat(gallery): add RealESRGAN anime upscaler * fix(stablediffusion): allow full-frame ESRGAN tiles * fix(routes): select explicit upscale models Give image upscaling dedicated usecase-filtered middleware and keep ordinary image models out of the endpoint. Mark and verify the legacy Diffusers x4 gallery model as an explicit upscaler. Assisted-by: OpenAI:gpt-5 [shell] * refactor(upscale): keep settings in backend options * test(config): keep upscale options backend-specific * fix: keep upscale routing metadata out of backend options --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
08871b1a6a |
feat(audio): add YuE2 music generation (#12617)
* feat(audio): forward sound generation params Pass string-valued sound generation parameters from the public request to the audio backend. Typed fields retain precedence over colliding generic parameters, and source audio remains unavailable in the public schema. Assisted-by: nib:gpt-5.6-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(gallery): add YuE2 music model Assisted-by: nib:gpt-5.6-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(audio): document YuE2 sound generation Assisted-by: nib:gpt-5.6-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(audio): reserve source input parameter Assisted-by: nib:gpt-5.6-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
855958960f |
fix(gallery): place context options at the root (#12590)
The Qwen3 template nests context_size, f16, and mmap under parameters, where the typed model configuration ignores them. Move these options to the root and correct three model-specific context overrides. Test the real gallery data and generated qwen3-vl-4b-thinking YAML. Document manual repair because template updates do not rewrite installed configurations. Fixes #12528 Assisted-by: nib:gpt-6-astra Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Plamen K. Kosseff
|
c03acb0647 |
feat(models): report per-model disk usage in API and WebUI (#12551)
New admin endpoint GET /api/models/storage reports disk usage of the installed models: each model's files and sizes, files shared between models counted once, and configured files that are missing from disk. The models WebUI page shows a usage summary, each model's file table, and the full file list with per-file status. Assisted-by: Claude Code:claude-fable-5 Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com> |
||
|
Ettore Di Giacinto
|
7467b51281 |
test(gallery): expect speaker_recognition on the bundles with a voice component
The parakeet-cpp backend now answers VoiceEmbed and VoiceVerify, so the pinning test asserts the usecase on the entries that declare it instead of its absence. Document voice_verify_threshold. Assisted-by: Claude Code:claude-sonnet-5-5 |
||
|
Ettore Di Giacinto
|
ce4099ea38 |
feat(gallery): declare speaker_recognition on parakeet-cpp bundles
The small and standard bundles have a voice component, and parakeet-cpp-realtime-scene-speakers loads a speaker encoder, so they can serve /v1/voice/* and the realtime voice_recognition stage. Add the usecase to their known_usecases and pin it in the gallery tests. Assisted-by: Claude Code:claude-sonnet-5-5 |
||
|
Ettore Di Giacinto
|
1d117292b1 |
feat(voice): name registered speakers through a bundle speaker component
Naming read only speaker_model:, so a parakeet-cpp bundle that sets speaker_component:voice never received the registered voices, in live transcription or in diarization. Resolve speaker_component: when speaker_model: is not set. A component is not an encoder file, so no file-name tag is derived for it: voices with a hash or family identity and untagged voices reach the backend, and a voice with only a file-name tag matches through the new optional speaker_tag: alias. speaker_model: still wins, including when it points at the bundle file. The bundle gallery entries do not declare speaker_recognition: that usecase means the VoiceEmbed and VoiceVerify RPCs, which the backend does not serve, and it selects the default model for /v1/voice/*. The pinning test now says so. Assisted-by: Claude Code:claude-sonnet-5-5 go golangci-lint |
||
|
Plamen K. Kosseff
|
104c2fb440 |
fix(oci): stage image downloads in a configured directory, not in /tmp (#12280)
* fix(oci): stage image downloads in a configured directory, not in /tmp
Problem:
- the image tar and its compressed layers staged in os.TempDir()
- /tmp is commonly a RAM-backed tmpfs far smaller than a backend image
- big installs failed with a full /tmp or silently ate RAM
Change:
- staging path resolved like the other storage paths
(LOCALAI_DOWNLOAD_STAGING_PATH, default ${basepath}/downloading),
threaded to the extractor as a download option
- every download works in its own subdirectory holding its tar and
layers: nothing shared between concurrent downloads, one removal
cleans a download up, a crash leaves one self-contained orphan
- callers that pass no staging directory keep the OS temp behavior
Assisted-by: Claude:claude-fable-5
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
* fix(oci): handle staging cleanup errors
Log staging cleanup failures to satisfy errcheck. Test extraction with an
unavailable OS temp directory and verify that staging is removed.
Assisted-by: Codex:GPT-6
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
---------
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
|
||
|
mudler-agentandEttore Di Giacinto
|
3185b6fcf8 |
feat(parakeet-cpp): load bundle GGUF files, bundle gallery entries, pin bump (#12479)
* feat(parakeet-cpp): load bundle GGUF files and use their components by role A bundle GGUF holds several models (ASR, VAD, diarization, sound events, speaker encoder) in one file, each with its own licence. Detect a bundle at load through parakeet_capi_bundle_components_json and open components with parakeet_capi_load_component. The three symbols are probed together, so an older libparakeet.so still loads plain files as before. The only ASR component is the primary model; bundle_asr:<name> picks one when there are several. A Silero VAD component of the primary bundle is loaded without an option and serves /v1/vad and vad:true. The diar, ced and voice components load on request: diar_component, sound_component and speaker_component, or a companion option (diarization_model, sound_model, speaker_model, vad_model) that names a bundle, even the model file itself. vad_component picks a VAD component and implies vad:true. A role the bundle cannot fill fails the load with the component list, and a diarization or sound request on a model without that role names the bundle components. Every existing option and single-file model behaves as before. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] * chore(parakeet-cpp): bump parakeet.cpp to 781a973 Brings in the bundle GGUF format and its C-API (parakeet_capi_load_component, parakeet_capi_bundle_components_json, parakeet_capi_load_error). Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] * feat(parakeet-cpp): gallery entries for the bundle GGUF files, docs Add parakeet-cpp-bundle-small (338 MB: Parakeet TDT+CTC 110M, Nemotron-3- Diarization, CED-Small, WeSpeaker ResNet34-LM, Silero VAD), -standard (1.1 GB, Parakeet TDT 0.6B v3 instead of the 110M model) and -moondream-redux (215 MB: packed Redux and Silero VAD, CPU only). One install serves transcription, VAD, diarization, sound events and speaker naming through the component options. The existing single-purpose entries stay. A bundle has no single licence, so the entries use license: other and state the licence and credit of each component in the description, with the upstream inconsistency of the CED licence. The docs get a section on bundles in audio-to-text with the entries, the roles, the options and the licence notice, and pointers from the VAD, diarization and sound classification pages. A gallery test checks the file names, checksums, usecases and options. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
ed4a3975be |
feat(parakeet-cpp): gallery entries for the VAD-only Moondream slices, pin bump (#12469)
* feat(parakeet-cpp): add gallery entries for the VAD-only Moondream slices Add parakeet-cpp-vad-moondream-redux and parakeet-cpp-vad-moondream-ultra. They install the VAD head of Moondream Redux and Ultra (Q8_0) as small files of 10 MB and 6 MB, cut out of the full models without retraining, for the VAD endpoint. The files cannot transcribe, and a transcription request fails with a clear error. The files load only with a parakeet.cpp build that has VAD-only GGUF support (parakeet.cpp pull request 87). The backend pin must move to a commit that includes it before these entries work in a released image. The parakeet-cpp-vad entry keeps installing Silero. The docs list the files with the size, load time and memory compared with loading a whole model. A gallery test checks the usecase, the file name and the checksum of each entry. Assisted-by: Claude Code:claude-sonnet-5-5 [golangci-lint] * chore(parakeet-cpp): bump parakeet.cpp to e53a253 Brings in the VAD-only GGUF loader. Assisted-by: Claude Code:claude-sonnet-5-5 [git] [gh] * docs(gallery): link the parakeet.cpp VAD docs instead of the merged PR Assisted-by: Claude Code:claude-sonnet-5-5 [git] --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
99043b442c |
feat(router): route with native decision models (#12449)
* fix(schema): preserve SystemOne image inputs Assisted-by: OpenAI * test(schema): follow Ginkgo conventions for decision inputs Assisted-by: OpenAI * feat(llama-cpp): dispatch native decisions through Score Upgrade the stock dependency and reconcile Score/TTS patches. Reuse native decision parsing, tasks, formatting and response-reader cleanup; preserve ordinary scoring admission and guard older dependencies. Assisted-by: OpenAI * refactor(systemone): share request and model validation Assisted-by: OpenAI:gpt-5 * fix(systemone): preserve HTTP wire-byte validation limit Keep structural validation separate from the serialized internal request bound so HTML escaping cannot reject valid HTTP payloads. Assisted-by: OpenAI:gpt-5 * feat(systemone): bound images and account native decisions Preserve public wire limits independently from router serialization. Reject unsupported NER images, map native request/capability errors, and stamp explicit usage once. Advertise decisions for stock llama-cpp. Assisted-by: OpenAI * fix(systemone): record usage on registered native route Exercise real registration and billing with a mock native backend. Reject empty native responses, malformed image URLs, trailing JSON, and wire overflow including whitespace. Assisted-by: OpenAI * feat(router): add lazy native decision transport Bind named models through internal ModelSystemOne calls with shared validation and bounded abandoned operations. Remove request and echoed-error contents from decision traces. Assisted-by: OpenAI:gpt-5 * feat(router): classify overlapping policies with native decisions Ask independent noul questions, validate probabilities and preserve first-superset routing. Wire the central factory with config-sensitive invalidation and cancellation-safe resolution. Document native framing and bounded operation limits. Assisted-by: OpenAI:gpt-5 * feat(gallery): add pinned Julia-1 native decision model Add a separate text-only llama-cpp Q8 entry with pinned Apache-2.0 source provenance and checksum. Installed using the gallery installer and exercised choice, score and noul on CPU. Assisted-by: OpenAI * test(router): verify native decisions through central factory Add an opt-in real-model Ginkgo integration covering the native Go loader and C++ transport, token usage, independent overlapping labels, and candidate selection. Document owned-server execution and the intentionally non-quality threshold. Assisted-by: Codex:gpt-5 * fix(llama-cpp): align upstream pin and preserve decision signatures Advance to bed0a856 without losing the automated upstream bump. Detect full-request fill_task support at compile time and forward every question for Nimble framing while retaining the earlier native signature. Preserve reconciled SCORE/TTS patches; add standalone compatibility coverage. Assisted-by: Codex:gpt-5 * feat(gallery): add native decision family defaults Pin Laya, Kev-4B, lev, OpenJev and Nimble artifacts. Verify Laya/Kev/lev gallery installs and CPU contracts on both native pins; clearly mark OpenJev/Nimble runtime validation pending and their noncommercial licenses. Assisted-by: OpenAI * docs(decisions): clarify integrated Nimble prerequisite Record the exact combined backend pin while retaining pending OpenJev and Nimble installation/runtime validation status. Assisted-by: Codex:gpt-5 * fix(gallery): indent native decision model sequences Match repository yamllint indentation for Laya, Kev, lev and OpenJev list fields. Parsed gallery data is unchanged; reproduce CI gallery lint failure before the whitespace-only fix and pass the same command afterward. Assisted-by: Codex:gpt-5 * docs(decisions): record OpenJev and Nimble CPU validation Record gallery installation, checksum/metadata verification and multiquestion native smoke results on bed0a856. Retain noncommercial and text-only limitations without accuracy or deterministic-output claims. Assisted-by: OpenAI * fix(ui): expose native Decisions router classifiers Select classifier models using metadata-driven capability routing, retain tuned thresholds, and validate native decision selections before saving. Cover both native backends and create/save/reopen in the real React editor. Assisted-by: Codex:gpt-5 * fix(router): exclude aliases from native decision discovery Check the originally named config before advertising native Decisions eligibility. Retain target capability inheritance for ordinary generation aliases. Exercise the actual capabilities endpoint with native models on both backends, aliases, and disabled models. Assisted-by: Codex:gpt-5 * feat(systemone): share bounded multimodal input validation Preserve text wire limits while admitting bounded PNG/JPEG decision input. Share collection and header validation across internal and public callers and keep the native runner response budget independent. Assisted-by: OpenAI:API-assistant * fix(systemone): bound admission lifetimes and validate complete images Retain shared admission leases through actual work completion, including abandoned internal operations. Decode bounded image pixels, cap public native responses before usage stamping, and preserve oversized malformed text status precedence. Assisted-by: OpenAI:API-assistant * fix(router): classify images before media fetching Preserve ordered structured probes for native decisions. Defer OpenAI media preparation until routing selects the served model, so rejected decision URLs cannot trigger downloads before shared validation. Guard direct image collection with context-aware shared admission. Keep text classifiers and embedding caches from discarding image input. Retain fail-closed classifier configuration and runtime fallback policy. Add middleware, typed-content, admission, cancellation and cache tests. Assisted-by: OpenAI:API-assistant * fix(router): bound extraction before serialization Check probe budgets before copying text or marshaling message state. Count JSON escaping so oversized internal inputs fail before allocation. Preserve typed Anthropic blocks through selected-model conversion and fallback. Keep retry coverage in Ginkgo without global test registration. Assisted-by: OpenAI * fix(router): bound supported probe serialization Arbitrary structs can bypass the probe budget through pointer marshalers, string tags, and promoted fields. Accept concrete chat schema types and plain JSON values instead of emulating arbitrary struct serialization. Budget escaped direct prompts before marshaling so raw length cannot hide serialized expansion. Preserve runtime fallback and reject oversized input before invoking the decision runner. Add Ginkgo allocation, boundary, and marshaler invocation regressions. Six-package tests, three-package race tests, and full-T2 delta lint pass. Assisted-by: OpenAI:GPT-5 golangci-lint * feat(decisions): enable bounded OpenJev images Validate native decision images before permissive media parsing and pixel allocation. Require both decision image support and a vision projector; missing or audio-only projectors cannot silently become text decisions. Pin the OpenJev Q8 projector and document its license and disk footprint. Add native safety tests, canonical limit parity, gallery and load-option checks, and a reproducible CPU direct-RPC contrasting-image smoke. Assisted-by: OpenAI:GPT-5 * fix(decisions): reject incomplete image streams stb accepts corrupt PNG Adler checksums and truncated JPEG scans. Use bounded zlib validation and strict libjpeg decoding before parsing. Keep dimension and aggregate pixel checks ahead of decoder allocations. Wire decoder dependencies into native builds and runtime packaging. Add regressions for appended EOI and embedded marker bypasses. Assisted-by: OpenAI:GPT-5 * fix(ci): gate native decision image validation Run the decoder security tests outside the stdlib-only native suite. Fetch vendor headers at the backend pin and provision decoder dependencies. Gate Go limit parity and production CMake wiring without model downloads. Assisted-by: OpenAI:GPT-5 * test(decisions): cover multimodal public API paths Exercise shared image contracts through the registered HTTP routes and external mock backend. Add opt-in cached gallery installation and real OpenJev image decisions through SystemOne and both routing APIs. Assisted-by: Codex:gpt-5 * test(decisions): assert isolation and cache bypass Observe external RPC calls and compare complete classifier history. Winner-only and cache-miss checks could hide dropped history or cache use. Give real inference its own application and model directory so shared backend mappings and loaded processes cannot affect mixed suite order. Assisted-by: OpenAI:ChatGPT * test(decisions): isolate fixture globals Disable optional global services in the isolated HTTP fixture and register cleanup before setup assertions. Verify meter provider identity survives fixture creation and destruction. Snapshot observed usage before assertions so failures cannot retain the mutex. Require a successful usage stamp before checking error responses. Assisted-by: Codex:gpt-5 golangci-lint * fix(application): honor optional telemetry controls Skip failover gauge registration when metrics are disabled. Register against the application meter rather than looking up the global provider. Allow embedders to retain the bounded routing log without billing stats. Keep the existing default when stats are disabled. The isolated HTTP fixture uses this option without losing its native router assertions. Assisted-by: Codex:gpt-5 golangci-lint --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
6c718fdda7 |
feat(parakeet-cpp): VAD (Silero and the Moondream head), vad_model option and gallery entries (#12463)
* feat(parakeet-cpp): implement the VAD call and add the vad_model option The backend now serves the VAD gRPC call (POST /vad and /v1/vad) with the standalone VAD of libparakeet. It accepts a Silero VAD GGUF as the model file, or an ASR model with a VAD head (Moondream Ultra and Redux). The request audio is float32 PCM at 16 kHz; the response lists the speech segments in seconds, like the silero-vad backend. A model with neither fails the request with the library message. The vad_threshold, vad_min_pause, vad_min_speech, vad_speech_pad and vad_max_segment options tune the segmenter. Unset values keep the defaults of the detector in use, and a bad value fails the load. The vad_model option names a Silero GGUF, resolved against the models directory like the other companion files. It lets any ASR model cut long audio at pauses through parakeet_capi_transcribe_path_json_vad_with, and it implies vad. vad:true alone still uses the model's own head. The new symbols are probed like the existing optional ones. A library without them still loads; the feature that needs one fails with a clear message only when it is used. Assisted-by: Claude:claude-sonnet-5-5 [go test] * feat(gallery): add parakeet-cpp VAD entries and a v3 plus Silero example Add VAD-only entries for the parakeet-cpp backend: the VAD heads of Moondream Redux (packed, CPU) and Ultra (Q8_0), which share their files with the existing ASR entries, and Silero VAD v6.2.3 as a GGUF (MIT, Silero Team). The parakeet-cpp-vad entry installs Silero; it has no variants, because variant ranking prefers the larger build that fits and these are different detectors. Add parakeet-cpp-tdt-0.6b-v3-silero-vad, a v3 entry that sets vad_model so long audio is cut at pauses by Silero. The Silero GGUF entries point at the intended Hugging Face URL of the file; the existing silero-vad entries are unchanged. A test checks the usecases, the shared files and the default entry and the vad_model reference. Assisted-by: Claude:claude-sonnet-5-5 [go test] * docs: describe parakeet-cpp VAD and the vad_model option Document the VAD endpoint on the parakeet-cpp backend (Silero GGUF and the VAD heads of Moondream Ultra and Redux), the vad_* tuning options, and the vad_model option that lets an ASR model without a VAD head cut long audio with Silero. Assisted-by: Claude:claude-sonnet-5-5 * chore(parakeet-cpp): bump parakeet.cpp to 6165e3d Pin the release that adds the standalone VAD (Ultra/Redux head and Silero) and the C API calls the backend now uses. Assisted-by: Claude:claude-sonnet-5-5 --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
b540c3e1fd |
chore(vllm-cpp): bump to 967883486 (ABI v30), add hf_overrides and Tev1 entries, fix vllm-cpp gallery installs (#12379)
* chore(vllm-cpp): bump vllm.cpp to 967883486 (ABI v30) Moves the pin from c3bebc357 to 967883486. On top of the Nimble decision adapter and the Qwen3.5 vision-loader fix, this brings Tev1 on /v1/systemone and vllm_decide (opt-in through a "Tev1Model" architecture in config.json), a tokenizer/ subdirectory fallback so the Laya HF snapshot loads as downloaded, a stop-token fix, a logprobs fix under async scheduling and a pinned parakeet.cpp fetch for the diarization build. ABI v30 only adds the diarization and speaker-attributed ASR entry points; no existing struct or signature changed, so the purego mirrors keep their layout and only abiVersion moves to 30. Between 4479dc99f and 967883486 vllm.h changed only in a comment. v30 turns VLLM_CPP_WITH_DIARIZATION on by default. The fetch is pinned now, but ON still downloads parakeet.cpp at configure time and links a second ggml into libvllm for calls this backend never makes, so build with the option off: the symbols stay present as refusing stubs. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-sonnet-5-5 * feat(vllm-cpp): add the hf_overrides engine arg vLLM parity: engine_args.hf_overrides is a JSON object of top-level config.json keys merged over the model directory's own config.json. The main use is opting a published checkpoint into an engine adapter its config does not name, such as {"architectures": ["Tev1Model"]} on the Tev1 snapshots, which declare Qwen3_5ForConditionalGeneration. The C ABI has no override input and the engine reads config.json from the directory it is given, so Load builds a private overlay directory: the merged config.json plus a symlink to every other entry of the model directory, and passes that to the engine. The download is never written. Free, a failed load and the next Load remove the overlay. validModelPath and the DFlash draft resolution still see the real directory. A value that is not a JSON object, a .gguf model or a directory without config.json fails the load instead of being skipped like an unknown engine_args key, because loading the unmodified config would serve a different architecture than the one configured. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-sonnet-5-5 * fix(gallery): nest vllm-cpp artifacts under overrides artifacts: is a model-config key, and the installer reads model-config keys only from overrides:. Five vllm-cpp entries (laya, gliner25-decide, qwen3-vl-4b, cua-s1-forms and gliner2.5) declared it at the entry top level, where it is silently dropped: the install reports success, writes a config whose model is the bare HF repo id and downloads nothing, and vllm-cpp (which does not infer artifacts) then fails the first load with "model path not found". Move each block under overrides:, and add a guard test that refuses a top-level artifacts: key in the index. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-sonnet-5-5 * feat(gallery): add Tev1 4B and 0.8B on vllm-cpp Two decisions entries for Together AI's Tev1 checkpoints, pinned to the current HF revisions. Tev1 is autoregressive: vllm.cpp answers /v1/systemone by scoring the option letters, and the same engine still serves chat completions. The published config.json names Qwen3_5ForConditionalGeneration, so each entry sets hf_overrides: {architectures: [Tev1Model]} to enable the decision route without editing the download. known_usecases is [decisions] only, since a declared decisions list is authoritative for reservation. The descriptions state what was checked: agreement with transformers on CPU over seven questions (4B 7/7, max probability difference 0.0004; 0.8B 6/7 with one near tie), CPU-only for the decision route, and a fine-tune license the model card says is still being finalized, so no license key is set. The Decisions API page lists both entries, drops the note that Tev1 does not serve /v1/systemone and documents the 24-option limit (Ollama allows 26). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-sonnet-5-5 --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
70ce62901f |
refactor: name the capability decisions instead of systemone
The usecase describes what a model can do, and the category is the Decisions API. SystemOne stays as the wire contract: the /v1/systemone routes, the Score RPC question_type and the swagger tag are unchanged. The usecase, flag, auth feature, UI label, gallery tags and docs page are now decisions. Assisted-by: Claude Code:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
c2af8d56ea |
feat(gallery): tag vllm-cpp entries by capability and add decision and vision models
laya declares the systemone usecase instead of chat. The gated Qwen3.6 27B NVFP4 entries gain vision; the 35B-A3B entries gain it as experimental because image input is not token-gated. Adds GLiNER2.5-Decide and Qwen3-VL-4B. A guard test keeps capability tags and known_usecases in agreement for every vllm-cpp entry. Assisted-by: Claude Code:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
2fa36e7147 |
feat(parakeet-cpp): speaker diarization, sound detection and live scene events (#12335)
* feat(parakeet-cpp): load diarization and CED models and companions
Repin PARAKEET_VERSION to parakeet.cpp PR #75's head, which adds
parakeet_capi_model_kind (ABI v8). Bind the new diarization, sound
event and combined scene stream C symbols through the same
purego.Dlsym probe pattern already used for the batched JSON entry
point, so the backend still loads against an older libparakeet.so.
Load now classifies the loaded GGUF by role (ASR, diarization or
sound) via parakeet_capi_model_kind and can load up to two companion
models from Options[] (asr_model:, diarization_model:, sound_model:,
paths resolved against opts.ModelPath), verifying each companion's
kind and freeing every context opened so far on any failure. Free
releases the primary and every companion. AudioTranscription now
names the loaded role when it is not ASR instead of a generic model
not loaded error. The dynamic batcher starts only when an ASR context
ends up loaded, primary or companion.
This is groundwork only: the Diarize and SoundDetection RPCs and the
live scene stream that actually use these new roles land in later
commits.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): reset role fields on a failed companion load
loadRoles' freeLoaded only released the C contexts it had opened; it
left ctxPtr/diarCtx/tagCtx and companions pointing at those now-freed
contexts, so a later Free() on the same instance would double-free.
Zero all four alongside the CppFree calls.
Also route AudioTranscriptionStream and AudioTranscriptionLive through
notASRError when ctxPtr is unset but a diarization or sound model is
loaded, matching AudioTranscription: both used to return the generic
model-not-loaded error instead of naming the loaded role.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parakeet-cpp): add speaker diarization
Implement the Diarize RPC for the parakeet-cpp Go backend, wired to
Nemotron-3-Diarization through libparakeet.so's diarization C-API.
Plain diarization uses parakeet_capi_diarize_pcm; when include_text is
set and an ASR companion is loaded, parakeet_capi_transcribe_and_
diarize_json fills each segment's text instead. Speaker labels are the
decimal index, or "unknown" for -1 (no diarized speaker overlaps).
min_duration_off merges same-speaker segments across a short gap
before min_duration_on drops the segments still too short, then ids
are renumbered. num_speakers/min_speakers/max_speakers/clustering_
threshold have no Sortformer equivalent and are logged at debug
instead of rejected.
Verified against the real Nemotron-3-Diarization + parakeet-tdt_ctc-
110m checkpoints on the two_speakers.wav fixture: correct A-B-A-B
speaker segmentation and matching speaker-attributed transcripts.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parakeet-cpp): add sound event detection
Wire the SoundDetection RPC to the CED tagger context (p.tagCtx)
loaded by Task 1's role classification. It runs the whole clip
through a one-shot parakeet_capi_sound_stream_* session (window
10s, hop 10s, top_k set to the tagger's class count so every
drained window carries a full score list), averages each class's
score across the drained windows, sorts descending, then applies
the request's threshold and top_k (0 keeps every class).
No tagCtx returns FailedPrecondition; a libparakeet.so missing the
sound_stream symbols returns Unimplemented. Every C call runs under
engineMu, and the stream is always freed, even when a feed or drain
call fails partway through.
Verified against a real ced-tiny-q8_0.gguf on the rooster.wav demo
clip: "Chicken, rooster" tops the list at score 0.91.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): cancel sound detection mid-feed, shrink the lock
SoundDetection now checks ctx before each 10 s feed slice (mirroring
driver.go's feedSlices) and returns Canceled if the caller gave up,
so a long clip can be interrupted instead of feeding to completion
regardless. The stream is still freed on every path, cancellation
included.
Also narrow engineMu to the C calls: the drained JSON document is
now decoded after the lock is released, splitting soundStreamScores
into a locked soundStreamDrain (opts, begin, feed, drain, free) and
an unlocked json.Unmarshal.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parakeet-cpp): stream speaker and sound events during live transcription
Add two additive proto fields, LiveSpeakerSegment and LiveSoundEvent,
repeated on TranscriptLiveResponse. When a diarization or sound
companion model is loaded, AudioTranscriptionLive now runs a no-ASR
scene stream (parakeet_capi_scene_stream_begin) beside the ASR
streaming session, feeding it the same PCM slices and forwarding any
closed speaker or sound events alongside the matching ASR delta, or
on their own when a slice has no ASR output.
The scene stream is freed and reopened on a mid-stream Config reset,
flushed with is_last before the closing FinalResult, and degrades
gracefully (a warning, not an error) when begin or a later feed call
fails, so live transcription keeps working ASR-only. Existing live
behavior is unchanged when no companion is configured, and no scene
C call is made in that case.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): keep scene events off the ASR critical path in live
Emit each slice's ASR result right after the ASR feed, before the
scene feed for that slice runs, so a companion diarization/sound
model never adds scene compute latency in front of the delta or
<EOU> that drives realtime turn detection. Closed speakers/sounds go
out afterward as their own response, so a slice with both now
produces two responses, ASR first. The live feed log line now
reports ASR and scene wall time separately.
Re-check the diarization/sound contexts a scene stream was begun
with against the live contexts before every feed, under the same
lock: Free() can race between an ASR feed and the matching scene
feed and free the model the stream borrows. A mismatch now returns
without touching the C side. Freeing the stream itself stays
unconditional; the scene stream's destructor only releases its own
buffers and never touches the borrowed contexts.
Also recover a panicking stub inside the live test goroutine instead
of crashing the test binary, and reset the live decode-lag tracker on
a mid-stream config reset, matching what its own comment already
promised.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(realtime): surface live speaker and sound events
Carry the backend's closed speaker segments and sound events
(TranscriptLiveResponse fields 7/8) through LiveTranscriptionEvent
as LiveSpeakerSegment/LiveSoundEvent (nanoseconds mapped to
seconds), and forward them from the semantic_vad live path.
Each speaker segment emits
conversation.item.input_audio_transcription.segment with speaker,
start, end and empty text under the turn's item id. Each sound
event emits conversation.item.sound_detection with one tag
(label, score = peak, index) and the event's new optional
start/end seconds fields, omitted when unset so the existing
unary/windowed sound-detection path is unaffected.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(realtime): keep start/end on a zero-second transcription segment
ConversationItemInputAudioTranscriptionSegmentEvent.Start/End used
omitempty, so a speaker segment starting at 0.0s dropped its
"start" key. Nothing emitted this event before the live scene-event
path, so drop omitempty: the segment always carries real times.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(gallery): add parakeet-cpp diarization, CED and realtime scene models
Add gallery entries for the new parakeet-cpp capabilities: standalone
Nemotron-3-Diarization, the same paired with the Parakeet TDT+CTC
110M ASR model for speaker-attributed text, CED-Tiny and CED-Base
sound classifiers, and a realtime scene bundle combining the
streaming EOU ASR model with diarization and sound companions.
SHA256 taken from the Hub API; licenses from each model card
(openmdw-1.1 for Nemotron-3-Diarization, apache-2.0 for CED,
cc-by-4.0 for the Parakeet ASR models).
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs: document parakeet-cpp diarization, sound detection and live scene events
Cover the new parakeet-cpp capabilities across the feature pages:
Nemotron-3-Diarization as a diarization backend (with and without
speaker text, the ignored speaker-count hints, the Sortformer
voice-like-sound quirk), CED as a sound classification backend, the
asr_model/diarization_model/sound_model/diarization_latency companion
options, and the realtime live speaker/sound events (event shapes,
the speech-turn-only limitation, and using this or
pipeline.sound_detection but not both).
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(gallery): correct the realtime-scene license and wording nits
parakeet-cpp-realtime-scene mistakenly copied cc-by-4.0 from the
existing realtime_eou_120m-v1 entry; the model card lists the NVIDIA
open model license instead. Switch to the gallery's usual spelling
for that license and keep the diarization/CED licenses called out in
the description.
Also: audio-diarization.md now says getting per-segment text needs
both an asr_model companion and include_text=true on the request, and
audio-to-text.md's option table reads "Use on" (a pairing the loader
does not enforce) instead of "Allowed on".
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): reject a companion role that duplicates the primary's
loadRoles let a companion option (asr_model:/diarization_model:/
sound_model:) assign into a role field the primary already occupied,
for example asr_model: on an already-ASR primary. The companion's
context silently overwrote ctxPtr/diarCtx/tagCtx, and Free() only
walks those three fields, so the original primary context was never
freed again.
Reject a companion whose role the primary already holds before its
GGUF is even loaded, freeing everything loadRoles opened so far, the
same way a wrong-kind companion is already rejected.
Also warn, rather than silently fall through, when
parakeet_capi_model_kind reports PARAKEET_MODEL_KIND_NONE for a
successfully loaded primary; the primary is still treated as ASR,
matching today's behavior.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): cap live scene sound score retention
sceneBegin started the live diarization/sound companion stream with
the C API's default sound options, whose top_k keeps 5 scores per
window forever until drained. The live scene path never drains sound
scores (only the offline SoundDetection RPC does, with its own fresh
stream), so this window queue on the C side grew for the whole
session's lifetime.
Set opts.Sound.TopK = 0 before starting the scene stream: this
disables score retention while leaving sound event detection (onset/
offset), which the live path actually consumes, unaffected.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): merge diarization segments per speaker, harden Diarize
mergeCloseSegments only compared neighbors in the single start-sorted
segment list, so two same-speaker segments never merged once another
speaker's turn fell between them (A, B, A): the short B segment broke
the adjacency the merge relied on. Group segments by speaker first,
merge within each speaker's own start-ordered run, then re-sort the
result by start so interleaved speakers come back out in timeline
order.
Also harden Diarize's entry points the same way streamFeedDoc/
sceneFeed already are: diarizeCall re-checks p.diarCtx (and, on the
include_text path, p.ctxPtr) under engineMu right before the C call,
so a Free() racing between Diarize's own checks and the lock can no
longer reach the C side with a freed context. When the include_text
call returns NULL, last_error is now read from both contexts and
whichever came back non-empty is reported, since either side of the
pairing can be the one that failed. A WAV decode failure is reported
as InvalidArgument instead of an unwrapped/untyped error.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): harden SoundDetection's engine checks
soundStreamDrain ran every C call under engineMu but never re-checked
p.tagCtx there, so a Free() racing between SoundDetection's own
tagCtx==0 check and this lock could still reach the C side with a
freed context. Re-check p.tagCtx under the lock and return
ModelNotLoaded when it was cleared, mirroring diarizeCall's own
re-check. A WAV decode failure is now reported as InvalidArgument
instead of an unwrapped/untyped error.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(parakeet-cpp): cover a mid-session scene feed failure
feedSlicesScene already degrades gracefully when a scene feed call
fails mid-session: it frees the broken stream and carries the ASR-only
session forward. Add a spec covering that path end to end: the scene
stream is freed exactly once, later audio slices still produce ASR
responses, and no speaker/sound events appear before or after the
failure.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs: fix the parakeet-cpp companion role table and realtime scene docs
audio-to-text.md's companion option table read "Use on" with a note
that the loader did not enforce the pairing; it now rejects a
companion whose role duplicates the primary's, so restore the
"Allowed on" wording and describe the real enforcement.
openai-realtime.md's live speaker/sound section claimed a mid-stream
session.update resets the companion stream and that it flushes on
session close; neither happens, since the realtime core opens one
live stream (and so one scene stream) per speech turn and closes it
at that turn's commit, with no mid-stream Config in between. Document
that lifecycle instead, state precisely that start/end are seconds
from the start of the turn's own audio, and note that the diarization
model starts a fresh session every turn, so a speaker index is only
meaningful within one turn. The example sound tag ("Rooster", index
17) did not match any real CED label; index 17 in ced-tiny-q8_0.gguf
is "Baby laughter". Replaced with "Chicken, rooster" at its real
index, 99.
Assisted-by: Claude:claude-sonnet-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(parakeet-cpp): use CED's real index for Chicken, rooster
The scene feed comment and the live test's canned document gave
"Chicken, rooster" index 365. In CED's AudioSet label list it is 99,
which is also what the realtime docs show.
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(realtime): call the test event accessor
The scene-event tests range over a method instead of its returned slice.
Call the synchronized accessor so the OpenAI test package compiles.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(parakeet-cpp): pin parakeet.cpp master with sound events
mudler/parakeet.cpp#75 (sound events, scene stream, model kinds) and
#74 (the missing <algorithm> include that broke the image builds) are
on master now. Pin 6dea76a instead of the #75 PR head, and update the
header comment the bump bot reads.
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(parakeet-cpp): pin parakeet.cpp with ced.cpp on main
parakeet.cpp #76 moved its ced.cpp submodule from the head of
localai-org/ced.cpp#3 (a branch-only commit) to ced.cpp main, where
#3 landed with an identical tree. Pin 623a968 so the image builds no
longer depend on that branch.
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(transcription): carry speaker labels on words and streamed segments
A diarizing backend could label transcript segments, but two paths
dropped the label: TranscriptWord had no speaker field, so live
transcription words and word-level timestamps could not carry one, and
the stream=true transcript.text.done event left the speaker out of
its segments.
TranscriptWord gains an optional speaker (proto field 4, additive).
It flows through the live event and result mapping, the JSON word
output of the endpoint and the CLI, and transcript.text.done now
includes a segment's speaker when there is one. Empty labels are
omitted, so responses without diarization are unchanged.
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
(cherry picked from commit
|
||
|
mudler-agentandEttore Di Giacinto
|
bc01ef2350 |
fix(gallery): keep model deletion inside the models directory (#12324)
listModelFiles gave utils.VerifyPath paths that it had already joined onto the models directory. VerifyPath joins its argument onto the base again, so an absolute path always passes and none of the four checks could fail. Model deletion then removed files outside the models directory: - A model name such as "../outside/victim" removed outside/victim.yaml. The in-process MCP delete_model tool passes the name from the tool call without a check. - A gallery file that lists a files: entry with "../" removed that file. listModelFiles now gives VerifyPath the relative names. InTrustedRoot also looped forever when a relative path was outside a relative root. filepath.Dir stops at "." for a relative path, and the loop waited for "/". The loop now stops when Dir returns its input. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
97ad8f1d70 |
fix(distributed): stage the files a model install declares (#12309)
* fix(distributed): stage every shard of a split GGUF A split GGUF is configured by its first shard only. llama.cpp opens the other "-0000N-of-0000M.gguf" files from the same directory by name. The router staged only the configured path, so the worker received shard 1 and the load failed with "failed to load GGUF split". The router now stages the remaining shards next to the first one. A missing shard fails the load and names the file. The file count for progress and the payload size also include all shards. The payload size feeds the load deadline and the disk-headroom check. For a 111 GB model whose first shard is 10 MB, both were sized for less than 1 GB. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): stage the files a model install declares Replace the split GGUF file name matching with the model's own file list. A gallery install or an import records every file of the model in ._gallery_<name>.yaml (files:), and a config can list more under download_files:. The router now stages all of these files, not only the files that the config's path fields name. This includes the other shards of a split GGUF, which llama.cpp opens by name. The application gives the router a resolver that reads the two lists. The resolver looks up the files by model name when it stages them, so a replica that the reconciler loads from saved load options gets the same files. backend.proto does not change. A declared file that is missing on the frontend is skipped with a warning. The load deadline and the disk headroom check include the declared files. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
490b952d06 |
feat(gallery): publish signed OCI fallbacks (#12182)
* feat(gallery): publish signed OCI fallbacks Publish both official gallery indexes with their local base configs so an outage of the HTTP and GitHub sources can fall back to Quay. Keep artifact signing policies separate from backend image policies, and expose each moving gallery tag only after its digest is signed. Assisted-by: Codex:gpt-6 * fix(gallery): confine packaged files to selected roots Use directory-scoped file access to reject symlink escapes during gallery packaging. Create private bundle files for the publishing runner. Assisted-by: Codex:GPT-6 --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
a95da0a46c |
fix(gallery): read the models dir once per gallery listing (#12283)
The cached gallery listing refreshed each entry's installed flag with one os.Stat per entry, under the cache's global write lock. A gallery holds about 1,900 entries. On a models directory on SMB, one refresh took about 14s. The listing and every row's VRAM estimate run this refresh, and the lock serialized them, so the models page took minutes to load. The installed check now lists the models directory once and looks up each entry in that listing. On the same SMB share the listing takes about 75ms. The answers match os.Stat: a symlink counts only when its target exists, and names with a path separator still use os.Stat. The listing runs before the lock is taken, so the lock covers only the flag updates. Concurrent callers on a cold cache now share one upstream load. Before this, each caller fetched the gallery index and the configs itself. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Plamen K. Kosseffandlocalai-org-maint-bot
|
6cfc99196d |
feat(gallery): read metadata for system-path backends, enabling variant aliases (#12141)
* feat(gallery): read metadata for system-path backends, enabling variant aliases Problem: - ListSystemBackends only read metadata.json for user-managed backends; the system-path scan (LOCALAI_BACKENDS_SYSTEM_PATH) was a bare directory walk with Metadata hardcoded nil - system-packaged backends (distro packages installing several accelerator builds of one backend) could not declare aliases or meta indirection at all, while gallery-installed backends could - surfaced while packaging LocalAI for Gentoo: the packages install cpu-/rocm-/vulkan-audio-cpp as system backends aliased to audio-cpp, which the server ignored Change: - scan each root separately, clean the system collection against the user-managed one, merge, then build and resolve — precedence lives in one explicit step - alias candidates carry their own metadata: the resolved alias entry can never pair one installation's executable with another's metadata, and it reports the chosen candidate's origin (IsSystem) - deterministic resolution: entries build in sorted name order and candidates sort by name at the resolution site, independent of scan order Precedence (user-managed always wins): - a user-managed backend hides a same-named system backend entirely - a user-managed variant takes over its whole alias family: the alias resolves among user-managed variants only and the system family's concrete names disappear — family versions move together, and a stale system variant may not work with newer models, so it must not stay reachable - a system variant's alias never hijacks a name that exists as a user-managed backend Tests: Ginkgo regressions for system-path aliasing, same-name hiding, family takeover, and the full metadata permutation matrix of cross-root name collisions (both directions, with and without metadata on each side). Docs: new "Backend Directory Format" section (run.sh, metadata.json, alias resolution — previously undocumented for user-managed backends too) and "System-Provided Backends" with the precedence rules. Assisted-by: Claude:claude-fable-5 Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com> * fix(gallery): preserve managed meta backends A system alias can replace a user-managed meta backend during discovery. Protect meta entries with the same precedence guard as concrete backends. Add a regression test and clarify the documented precedence. Assisted-by: Codex:GPT-6 Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com> --------- Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
mudler-agentandEttore Di Giacinto
|
543fb4bd24 |
fix(gallery): verification follow-ups for oci:// galleries (#12243)
* fix(gallery): verification follow-ups for oci:// galleries Follow-ups from the post-merge review of #12238 and #12239. Only a policy decision is a refusal now. cosignverify wraps ErrPolicyRejected around a failed signature check, an identity or source-repository mismatch, a not_before cutoff and a missing or unparseable bundle. A TUF, registry or network failure during verification, or a timeout, is an outage: the gallery falls back to the copy verified under the current policy, as it does when the registry is down. An oci:// gallery with a verification block, or any oci:// gallery under strict integrity, is no longer answered by an https://, github: or file:// mirror. Such a mirror is ignored with a warning, because nothing can check its signature. The index of an HTTP gallery, whose policy only covers its backend images, is cached under the URL-only name again, so no unchecked body is stored under a policy-keyed name. The in-memory index cache key now includes the policy. After a runtime policy change the index is fetched again, and entries with a relative url install again. The registry digest lookups after install and upgrade, and in the upgrade check, run only for real registry references (new URI.LooksLikeRegistryOCI), not for ollama:// or ocifile://. The refusal message names strict integrity when that is the cause, and the gallery name is no longer repeated. Specs pin the URL-only cache name for galleries without a policy, a fixed key for a fixed policy, and that every GalleryVerification field changes the key. The docs describe refusal, outage, mirrors and strict integrity. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gallery): reset listings on gallery changes, classify referrer outages Review follow-ups for this PR. The React UI lists from AvailableGalleryModelsCached, which is keyed by nothing. A gallery change through the settings API or a runtime_settings.json edit now drops that listing when the model or backend gallery configuration differs. Before, the UI kept the old list, with local paths into the old policy's tree, until the next background refresh, or for good when the new policy refused the gallery. In cosignverify, a referrer the registry fails to serve now makes the lookup an outage whatever other referrers failed and in any order, since the unread one may be the valid signature. An invalid policy (Validate in NewVerifier, an unparseable not_before) is ErrPolicyRejected, because no fetch can make it usable. The docs say that only an oci:// gallery with a verification block skips non-OCI mirrors, and list an unusable policy as a refusal. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
f5c4083d7e |
fix(gallery): tie oci:// gallery caches to the verification policy (#12239)
The unpacked oci:// gallery cache and the last known good copy of the index were keyed on the gallery URL only. After an operator tightened a gallery's verification policy (added source_repository, moved not_before forward), content verified under the older policy, or under none, was still served for up to an hour from the unpacked cache, and indefinitely from the last known good copy while fetches failed. A fetch refused by signature verification also fell back to that last known good copy, so a refusal became a silent downgrade. Turning strict integrity on did not stop an unverified cached copy from being served either. Name both caches by the URL plus a stable hash of the policy. A gallery without a policy keeps its old URL-only name, so existing caches stay usable. A fetch refused by the policy, or by strict integrity, is now reported and never answered with a cached copy; a network failure still falls back, but only to a copy verified under the current policy. The strict integrity check runs before the cache is read. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
3278b4a2ed |
fix(gallery): strip the oci:// scheme before every registry lookup (#12238)
A backend installed from an oci://host/repo:tag or oci://host/repo@sha256 URI was downloaded correctly, but the digest lookup that follows the install (and the one after an upgrade) passed the raw URI to the registry client. The client does not know the oci:// scheme: with a port in the host it failed to parse the reference, without one it read "oci" as the registry host and queried https://oci/v2/. The install still succeeded, so the only trace was a warning and an empty digest in metadata.json, which made the next upgrade check report an upgrade for no reason. Add downloader.URI.OCIReference and route every consumer that hands an OCI URI to a registry client through it: the install and upgrade digest lookups, the upgrade check, the OCI download path, the oci:// gallery fetch and the llama.cpp importer. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
be0671c635 |
feat(gallery): optionally pin the signing certificate's source repository (#12235)
* feat(cosignverify): optionally pin the certificate's source repository Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(gallery): source_repository in the verification policy Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(gallery): when source_repository is checked; test the issuer Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
237cf456fd |
feat(gallery): galleries published as OCI artifacts (#12167)
* feat(oci): pull ORAS artifacts into a directory Galleries published to an OCI registry arrive as an ORAS artifact whose layers carry their tree path in org.opencontainers.image.title. Nothing in pkg/oci could read a non-image manifest, so add PullArtifact: it lays the layers out under a destination directory and returns the manifest digest so callers can pin and verify signatures on it. A registry is remote input and this writes files, so the manifest is validated before any byte is fetched. A title that is absolute, escapes the destination or is missing is refused, an artifact of an unexpected artifactType is refused, and both the layer count and the total size are capped with caller-settable limits. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-5 [Claude Code] * feat(gallery): fetch and verify galleries published as OCI artifacts A gallery whose URL is oci://host/repo:tag is now pulled as an ORAS artifact and its index.yaml read from the unpacked tree, alongside the existing HTTP and file sources. Mirrors, the per-candidate timeout, the failure cooldown and the last known good copy work the same for both schemes, so a gallery can mirror an OCI primary with an HTTP fallback. When the gallery declares a verification policy the artifact reference is resolved to its manifest digest, the publisher signature is checked against that digest, and only then is the same digest pulled. Nothing unverified is written to disk or parsed. With strict integrity mode on, an OCI gallery without a verification policy is refused instead of warned about, which is what the flag already does for backend installs. The pull lands in a staging directory that is renamed into the cache only once the whole tree is on disk and the index reads back as an index, so a failed or interrupted pull leaves nothing a later fetch would serve. A fetch that finds a fresh cache entry does not contact the registry. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-5 [Claude Code] * feat(gallery): resolve entry urls relative to the gallery root A gallery published as a self-contained tree, which is what an OCI gallery is, names its base configs by their place in that tree. Such a url reached the HTTP client verbatim and no entry of the gallery could be installed. A scheme-less entry url now resolves against the root the index came from: the unpacked artifact for an oci:// gallery, and the directory of the index URL otherwise. The relative path may not climb out of that root, reusing the guard the artifact puller already applies to layer titles, and an entry that does is dropped from the listing rather than failing the whole gallery. An entry that names its own scheme is untouched, so .ref indirection and local github: resolution behave as before. Reading an entry of an OCI gallery also needs the unpacked artifact directory as its trusted root, since the cache is deliberately a sibling of the models directory the downloader otherwise confines a file read to. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-5 [Claude Code] * fix(oci): restrict artifact file permissions Create artifact files with owner-only permissions to satisfy G302. Document the existing path validation for the G304 scanner finding. Check the permissions of downloaded layers in the artifact test. Assisted-by: Codex:gpt-6 gosec * fix(oci): confine artifact writes to their root Use root-relative filesystem operations to reject escapes through existing directory symlinks. Retain owner-only permissions and add a symlink escape regression test, without suppressing the path traversal finding. Assisted-by: Codex:gpt-6 --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
mudler-agentandEttore Di Giacinto
|
4d5ea12c3b |
fix(gallery): strip oci:// before upgrade-check digest lookup (#12138)
GetImageDigest calls name.ParseReference, which cannot parse the oci:// scheme. Self-hosted registries must set the scheme to be recognised by LooksLikeOCI, so without stripping it they silently lose upgrade detection. Strips the prefix at the call site, matching what the other two call sites already do (pkg/downloader/uri.go, gallery/importers/llama-cpp.go). Supersedes #12120 (DCO not signed by contributor, branch had unrelated history needing rebase). Assisted-by: MAKI:regolo/glm5.2 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Richard Palethorpe
|
2facfc0d88 |
feat: Add kimodo.cpp and 3D animation API/UI (#12095)
* fix(vulkan): preserve host ICD discovery for packaged backends Add bundled Mesa manifests through VK_ADD_DRIVER_FILES instead of replacing the system driver list. Merge inherited and model-specific additive paths while preserving explicit operator overrides, with regression coverage. Assisted-by: Codex:gpt-5 golangci-lint Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(3d): add Kimodo CPU and Vulkan animation backend Introduce a distinct animation capability and model-described 3D operations, with a typed /3d/animate API, RPC transport, distributed media staging, permissions, and tracing. Add a persistent kimodo.cpp adapter, skeleton GLB export, CPU/Vulkan packages, model and backend galleries, importer support, CI builds, and documentation. Adapt Studio inputs to each model and provide real-time skeleton playback, seeking, and history. Cover backend validation, packaging, API behavior, importer inventories, distributed staging, and Studio workflows. Validate real-model CPU/Vulkan generation and deploy the integration to the local QA instance. Assisted-by: Codex:gpt-5 golangci-lint Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(kimodocpp): adopt monolithic encoders and resident inference Update upstream for resident weights, packed execution paths, and cached motion graphs. Default to all 32 text layers while retaining configurable streaming and legacy bundle support. Use monolithic Q8_0 encoders by default and offer all six published quantizations through the gallery and importer. Refresh pinned hashes, tests, and documentation; remove the obsolete thread patch and ensure cached source checkouts follow the upstream pin. Validated CPU and Vulkan generation, lower-bit streaming, gallery/importer suites, packaging, lint, and cold/warm Studio generation on localai-dev. Assisted-by: Codex:gpt-5 golangci-lint Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
Ettore Di Giacinto
|
a398c559b3 |
fix(gallery): persist inference defaults under parameters
Gallery installs merged family defaults at the YAML root and only re-marshaled them on the artifact path. Persist the defaults in the loader-visible parameters map for every install path while preserving authored overrides. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacintoandxingyifeng
|
df70ff311d |
feat: add FunASR speech recognition backend (#10090)
Adds FunASR/SenseVoice as a Python backend for speech-to-text with support for CPU, CUDA 12/13, ROCm, Intel SYCL, L4T, and Apple MPS. Co-authored-by: xingyifeng <xingyifeng@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
878b99384f |
feat(audio-cpp): add ROCm backend image
The pinned audio.cpp revision supports HIP, but LocalAI neither builds a ROCm image nor accepts its backend option. AMD hosts therefore fall back to the CPU image. Build and publish the HIP variant, connect it to AMD capability selection, and accept both upstream HIP names. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
b845468a11 |
fix(ds4): resolve Hugging Face repository imports (#11340)
fix(ds4): resolve repository imports to GGUF Select a concrete DeepSeek V4 Flash GGUF from Hugging Face metadata while honoring quantization preference order. Reject unresolved repository imports instead of emitting an invalid bare URI. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
561d623976 |
feat(gallery): add EXL3 vllm.cpp models (#11912)
* docs: design EXL3 gallery entries Define the pinned Qwen3.8 and DeepSeek V4 Flash entries before changing the gallery. Assisted-by: Codex:gpt-5 [web] * feat(gallery): add EXL3 vllm.cpp models Add pinned Qwen3.8 and DeepSeek V4 Flash configurations. Bind the staged DFlash companion path so vllm.cpp opens LocalAI's managed snapshot. Assisted-by: Codex:gpt-5 --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Dimitris Karakasilis
|
8aeea4cdde |
fix(gallery): persist inference defaults where the loader reads them (#11232)
The recommended sampling parameters for a model family were applied at install and then never took effect. Two things went wrong on the way to disk. They were written as top level keys. ModelConfig embeds PredictionOptions under the "parameters" yaml key, so temperature, top_p, top_k, min_p, repeat_penalty and presence_penalty are only read from there. At the top level they parse without error and are then ignored for the life of the model. They were also merged in after the YAML had already been marshalled. The only re-marshal sat behind the artifact binding, which an entry carrying files: never reaches, so for those entries the defaults were computed and then dropped before anything was written. Neither failure was visible in normal use. ApplyInferenceDefaults runs again at load time and fills the same values from the same table, so the model ends up tuned correctly while the file on disk pins nothing. It surfaces when someone edits one of those values expecting it to win, or when a family is absent from inference_defaults.json and there is nothing to refill from. Both install paths are covered: an entry carrying files:, and one that binds a primary artifact instead. The empty base spec asserted that the authored parameters block landed verbatim. It now checks the authored keys individually, because the family defaults are merged into that same block. Assisted-by: Claude:claude-opus-5 Signed-off-by: Dimitris Karakasilis <dimitris@karakasilis.me> |
||
|
lei_lei
|
b8316f2a2a |
fix(gallery): use published F16 mmproj for qwythos-9b (#11792)
Install 404s because the gallery still points at mmproj-...-f16.gguf. HF only ships ...-F16.gguf now, with a different sha256. Signed-off-by: lei_lei <96427312+leilei3167@users.noreply.github.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
29899cd1e0 |
fix(ui): size model fit against the cluster and move node labels into the selector (#11765)
* fix(ui): move node labels into the scheduling selector field The scheduling page kept a node-label browser open above the rules whether or not anyone was writing one, while the field that actually needs labels, the rule's node selector, was two bare text inputs with no hint of what the cluster reports. The browser is gone. The selector's key input now completes against the label keys the cluster uses, and the value input offers only the values that key takes. The roster already loads for the page, so the suggestions cost no request, and a roster that fails to load costs the admin the hints and nothing else. Suggestions stay suggestions: a key no node reports yet still commits as typed, which is how an admin writes a rule before labelling the nodes for it. Assisted-by: Claude:claude-opus-5 golangci-lint eslint playwright Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): size model fit against the cluster, not the frontend The models page asked the frontend how much memory a model may occupy. In distributed mode the frontend is usually a GPU-less pod while every model runs on a worker, so a fleet of GPU nodes was told it could only run the smallest CPU build. The variant picker's fits flag and its auto-selection came from the same place, as did the hardware recommendations. The registry now reports the largest single healthy backend node. The largest node, not the fleet total: a model loads into one node, so four 16GB workers are not a home for a 40GB model. An operator-set VRAM budget caps a node's contribution, because the scheduler refuses a load above that ceiling anyway, and a GPU node beats a CPU node holding more system RAM. GET /api/resources and GET /api/models carry this as an additional cluster object. Their aggregate and ram fields keep reporting the frontend's own hardware, which is what the resource monitor shows. Variant selection judges backends against the union of the capabilities present in the cluster, the way backend discovery already did. Every path degrades to the local host: no cluster object in single-node mode, and none when the registry cannot be read, so a hiccup narrows the answer back to single-node behaviour rather than marking the whole catalog too large. The verdicts now name the node they belong to, since a model fits somewhere or nowhere. Assisted-by: Claude:claude-opus-5 golangci-lint eslint playwright Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
8f56e4e042 |
fix(vram): persist remote probe metadata (#11487)
* fix(vram): persist remote probe metadata The startup warmer repeated remote size and GGUF metadata probes after every restart because both caches lived only in memory. Store successful HTTP probes for 24 hours so frequent restarts reuse the prior results. Bound the cache, reject invalid records, and purge it when gallery data changes. Local model files continue to bypass persistence. Assisted-by: Codex:gpt-5 * fix(vram): check temporary file cleanup The lint gate rejects the unchecked cleanup call in the persistent cache writer. Assisted-by: Codex:gpt-5.6 [golangci-lint] * fix(vram): make persistent cache optional Remote metadata probes can transfer enough data that operators need control over disk reuse and startup warming. Gallery autoload now gates both behaviors, and the runtime setting applies changes immediately. Assisted-by: Codex:gpt-5 * fix(ui): expose gallery startup pre-warm The existing gallery autoload setting also gates the startup metadata warmer. Name both effects in Settings so operators can find the requested boot control. Assisted-by: Codex:gpt-5 --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
2383726d6d |
Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)
Revert "chore(tests): Avoid network, sleep and more during tests (#11050)"
This reverts commit
|
||
|
Richard Palethorpeandlocalai-org-maint-bot
|
cb3bf7af3f |
chore(tests): Avoid network, sleep and more during tests (#11050)
* test: make coverage failures observable Keep per-root logs, reject concurrent coverage runs, and avoid relying on /bin/sleep in the worker timeout test. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: parallelize coverage without remote fixtures Assisted-by: Codex:gpt-5 [apply_patch] [exec_command] Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: add offline resource infrastructure Introduce versioned resource manifests, a checksum-verified CAS preparer, offline test wrappers, and a guarded network transport. Replace live Hugging Face, GitHub, and OCI cases with deterministic fixtures and inject fixture metadata into importer discovery. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: enforce offline resource replay Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: harden offline resource refresh Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: expose slow coverage waits Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: eliminate avoidable wall-clock waits Inject a clock into Hugging Face retry handling, reuse a process-scoped PostgreSQL container with per-spec schemas in the nodes suite, and poll local import jobs promptly. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: remove repeated fixture startup waits Share PostgreSQL fixtures across parallel endpoint and agent suite workers, and make the worker Free deadline injectable so the wedged-backend test does not spend five seconds on wall-clock time. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: fix offline resource CI portability Normalize Docker archive metadata before content addressing, derive archive checksums during explicit refreshes, make network lint portable to macOS, and prepare distributed images before running their offline suite. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: cache Go modules before offline tests Warm the complete module graph before the Linux and macOS test jobs enter offline replay mode, so tool dependencies such as Ginkgo are not fetched through the guarded proxy. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: drop the static network lint in favour of real isolation The offline test suite already prevents tests from reaching the network twice over: run-test-linux-offline.sh puts the test process in a cgroup and REJECTs egress outside the private ranges, and HardenedTransport installs testnetwork.LocalGuard to refuse dials that resolve to a public address. Both fail the test with a precise error at the moment of the dial. test-network-lint.sh added neither. Its diff stage defaulted to a HEAD base, so on a clean checkout it compared the tree against itself and inspected nothing; the branch's own commits were never examined. It only produced output when an earlier job step dirtied the tree, and then it matched a bare https?:// against whatever changed. make react-ui runs npm install rather than npm ci, so CI rewrote core/http/react-ui/package-lock.json and the lint reported an npm registry URL as forbidden test network access: + "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.25.tgz", Its fingerprint stage was self-defeating in a quieter way: hashing the whole tree's network-mechanism inventory meant every rebase onto a master that touched any _test.go needed a manual baseline bump, so the check mostly caught its own staleness. Remove the script, its make target and the two prerequisite edges, along with the test-network: fixture markers that existed only to suppress it. The isolation itself is untouched. Assisted-by: Claude:claude-opus-5 [go vet] Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: keep hidden files in the offline test bundle artifact Cherry-picked from 15a37b0ac on the remote branch. The offline bundle lives under .cache/, which actions/upload-artifact skips by default, so the Linux job packed an artifact missing the very file the next step restores. The other half of 15a37b0ac moved test-network-lint out of the `test` and `test-coverage` prerequisite lists into a recipe line, so parallel make could not fingerprint the tree while generated fixtures were still changing. That is dropped: the preceding commit removes the lint entirely, and the race it worked around is one more reason a whole-tree fingerprint was the wrong mechanism. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * refactor: share bounded exponential backoff Use overflow-safe saturating arithmetic for retry delays across model import polling, downloads, registration, node operations, and model loading. Keep model import status checks responsive initially while capping their interval at 500ms. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: mirror Jetson Python wheels Keep the CUDA aarch64 wheel subset in GHCR and serve it as a local PEP 503 index during L4T backend builds, preserving last-known-good packages through upstream outages. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * docs(agents): index the Jetson wheels mirror Mention the GHCR-hosted L4T wheel mirror in the CI caching guide summary so maintainers can find its outage and cache documentation. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: add defensive build network proxy Record build destinations and byte counts, retry observable idempotent HTTP downloads, and isolate explorer database tests that race under coverage. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(kokoros): implement updated backend trait Return unimplemented for image upscaling, matching the backend's other unsupported modalities after the protobuf API update. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): clear recovered proxy errors Do not mark a request failed when a later safe retry succeeds. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: require HTTPS build interception Inject a short-lived proxy CA into BuildKit and Dockerfile RUN steps, reject plain HTTP and opaque tunnels, and retain method/status/byte telemetry for verified HTTPS traffic. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): preserve system trust in unproxied builds Mount the generated interception CA at a dedicated secret path and add it to the trust bundle only in proxy-aware dependency stages. This prevents optional secret mounts from masking the system CA bundle in ordinary backend test builds. Install the requested Go toolchain before starting the proxy and satisfy cleanup error checks found by CI lint. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): persist build proxy trust Install the generated proxy CA through the system-managed local certificate directory so ca-certificates upgrades retain it. Avoid turning canceled matrix jobs into proxy cleanup failures. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): trust proxy in nested build scripts Install the build proxy CA before nested source fetches, route the DS4 package setup through the HTTPS mirror helper, and avoid repeated OCI setup in gallery behavior tests. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): use HTTPS apt sources for Bonsai Rewrite ARM64 package sources before installing GCC and check gallery fixture cleanup errors so the optimized tests satisfy errcheck. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(privacy-filter): trust build proxy CA Install the mounted build proxy certificate before privacy-filter's make target fetches its HTTPS sources, for both source and prebuilt builder paths.\n\nAssisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: fail on hidden offline egress Count cgroup-scoped firewall rejects and fail the offline test harness with bounded aggregate diagnostics. Inject the gen-audio GGUF probe so fixture-backed importer tests do not attempt real network access. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): preserve system CA trust Build a combined runner certificate bundle instead of replacing public roots with the generated proxy CA. Centralize additive container installation in the shared proxy CA helper. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
0647939953 |
fix(gallery): repair DeepSeek V4 fallback (#11480)
The DeepSeek V4 Flash base entry points at a Hugging Face repository page instead of a GGUF object. When variant probing cannot rank a concrete build, the base fallback downloads no usable model weights. Use the validated IQ2XXS object and checksum already shipped by the q2 variant. Pin that payload in the gallery resolution test. Assisted-by: Codex:gpt-5.6 Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
|
3ec466b61b |
chore: ⬆️ Update ikawrakow/ik_llama.cpp to 26ceed9d4091a1696cf50e2ed87e5767d5811d81 (#11475)
* ⬆️ Update ikawrakow/ik_llama.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * fix(gallery): align Higgs Audio checksum test The validated gallery checksum changed in #11459, but its dedicated regression assertion kept the previous value and now fails the master test suite on Linux and macOS. Assisted-by: Codex:gpt-5.6 --------- Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
16193e1982 |
feat(gallery): add Higgs Audio v3 TTS (#11456)
Expose the existing audio.cpp Higgs support as an installable Q8 gallery model and document voice cloning and licensing constraints. Assisted-by: Codex:gpt-5 Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
7b9167eaad |
feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend (#11392)
* fix(config): do not read a TTS speaker-encoder mmproj as vision support Qwen3-TTS on llama-cpp ships an mmproj holding the speaker encoder and code predictor. VisionSupported() treated any non-empty MMProj as proof of image input, so every such model would be advertised as vision-capable. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(llama-cpp): add TTS request option parsing helper Validates text and speaker reference presence and strictly parses the top_k / top_p per-request params, in a header with no llama.cpp or gRPC dependencies so the standalone C++ unit test gate picks it up. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(llama-cpp): range-check the TTS top_k and top_p request params Format validation alone let NaN, infinity and out-of-range values through. The consumer copies both values into the audio generation input unconditionally and only guards its separate sampler assignment with "> 0", a test NaN also fails, so a NaN reached llama.cpp with the guard never firing. top_k must now be >= 0 and top_p must fall within 0.0 to 1.0 inclusive, with the bound written as a negated in-range test so NaN is rejected rather than silently accepted. Also cover the two checks the suite could not previously kill: the whole-string check in the float parser and the int32 range check. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(llama-cpp): bump pin to f9e832c10 and carry the TTS server task Picks up ggml-org/llama.cpp#26254 (Qwen3-TTS via mtmd) and #26536 (the short-input audio chunk fix). Adds 0002-add-server-task-type-tts.patch, the server-side half of the still-draft #26603, so TTS runs through the slot scheduler instead of racing it. Remove that patch when #26603 merges. The patch is rebased on top of the score patch: its tokenize-switch hunk collided with the SERVER_TASK_TYPE_SCORE case, and its lone SRV_WRN call passes no variadic argument, which the macro cannot expand. The score patch itself needed no refresh. Also fixes fallout from the bump in grpc-server.cpp: upstream dropped the per-slot n_ctx argument from server_schema::eval_llama_cmpl_schema. Only the schema branch loses it, since forks predating the server-schema split still expect the old argument list. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(llama-cpp): implement the TTS and TTSStream RPCs Both were declared in backend.proto but unimplemented. They now submit a SERVER_TASK_TYPE_TTS task and drain the response reader, the same shape PredictStream uses. The streaming path emits a leading sample_rate message and then raw PCM, because ModelTTSStream builds the WAV header itself; the non-streaming path emits a complete WAV to the requested dst. The streamed samples are converted from the pipeline's float32 to signed 16-bit first. MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM hands back floats, while the header ModelTTSStream writes announces 16-bit samples, so shipping the floats verbatim would decode as noise. prepare.sh and CMakeLists.txt now stage tts_request_options.h alongside the other grpc-server helpers, and register its standalone test with ctest the way passthrough_options_test is registered. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(llama-cpp): mask non-codec tokens for Qwen3-TTS generation The Qwen3-TTS gen-audio pipeline maps a sampled backbone token to a codebook row with an unchecked subtraction, in mtmd-helper-gen.cpp: inp.code0 = sampled - codec_0; For ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF the vocab is 155008 tokens, <|codec_0|> is 151936 and the codec codes end at 153983. The model's own tokenizer.ggml.suppress_tokens holds 1023 ids covering 153984..155007, every special above the codec range except <|codec_eos_token|> (154086) which stays reachable as the stop token. Nothing masks the text range 0..151935, so the backbone can sample a text token at any step, the subtraction goes negative, and ggml_compute_forward_get_rows aborts the whole backend process on GGML_ASSERT(i01 >= 0 && i01 < ne01). Complete the mask upstream started: bias every token below <|codec_0|> to -INFINITY for TTS tasks so only codec codes and the codec EOS remain reachable. The biases are appended to task.params.sampling.logit_bias, which common_sampler_init already merges with the model's suppress tokens into one llama_sampler_init_logit_bias, so no sampler is added to the chain. Measured cost is 0.082 ms per sampled token and 1.16 MB, set against a forward pass in the multi-millisecond range. It lands in launch_slot_with_task rather than in a route handler so that llama.cpp's own POST /tts and LocalAI's TTS/TTSStream RPCs are both covered, and <|codec_0|> is resolved from the vocab rather than hardcoded so a model without it is left alone. This is reproducible with upstream's own llama-tts and no LocalAI code loaded, aborting at frame 55 on Q4_K_M and frame 71 on Q8_0, so it is neither a quantization artifact nor an artifact of the gRPC adapter. Two further defects in the same draft pipeline still prevent end-to-end audio; they are independent of this one and are recorded in the task report for an upstream bug report. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(llama-cpp): bump pin to 9de0fcf2b and drop the TTS codec mask Upstream fixed the Qwen3-TTS abort in ggml-org/llama.cpp c8e03ce81 ("mtmd/ggml: add ggml_build_forward_order", #26649), landed one hour after the previous pin. ggml_build_forward_expand marks a tensor and all its ancestors for compute, so using it as a pure ordering hint defeated ggml_build_forward_select and made GEN_WAV calls execute the GEN_CODE branch against a stale inp_code0, hitting the get_rows bound assert in ggml_compute_forward_get_rows. That single defect accounts for every abort seen on this model, so 0003-mask-non-codec-tokens-for-tts.patch is removed rather than rebased. The mask changed the observed behavior, but it was perturbing a graph ordering bug rather than fixing a sampling one: at the new pin the whole path works without it. Keeping it would have meant carrying a 152k-entry logit bias, and rebasing it on every pin bump, for no benefit. Verified at 9de0fcf2b with only 0001 and 0002 applied, which both apply clean with no fuzz and needed no rebase: non-streaming HTTP 200, 410924 bytes, 8.56 s RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit, mono 24000 Hz streaming HTTP 200, 560684 bytes, 11.68 s, exactly one RIFF at byte 0, same format, which also exercises the float32-to-s16 conversion at runtime for the first time Pristine unpatched llama-tts at the same pin now also completes, 130 frames to a valid WAV, where it aborted at frame 55 before. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(llama-cpp): clear the TTS slot sequence between requests Only the first TTS request in a backend process succeeded. Every later one failed instantly, in about 0.13 s, with "TTS prompt processing failed" from step_prompt, regardless of streaming or non-streaming and regardless of the text. With LOCALAI_SINGLE_ACTIVE_BACKEND=true the process is kept alive between requests, so a deployment would have served exactly one utterance per backend start. The cause is missing KV hygiene, not anything in the gRPC adapter. TTS slots never enter the shared batch: pre_decode() returns early for them and process_tts_slots() drives them instead, so they skip the prompt-cache bookkeeping that clears a slot's sequence between requests. Nothing in the gen-audio path makes up for it: mtmd_helper_gen_audio_reset only clears host-side buffers, and the pipeline always decodes from position 0 into the sequence identified by slot.id. So the second task on a slot writes positions 0..N over the first task's tokens and llama_decode fails. Fix is one call to slot.prompt_clear(), the same helper the normal path uses, in the SERVER_TASK_TYPE_TTS branch of launch_slot_with_task before set_input. It goes into 0002 rather than a new patch file because it is a defect in the code that patch introduces, and the header now records it as ours so we know whether it still needs carrying if #26603 merges without it. Verified in one backend process, different text on every request: three consecutive non-streaming requests, three consecutive streaming requests, and an interleaved non-streaming, streaming, non-streaming, streaming run. All ten returned HTTP 200 with RIFF ... WAVE audio, Microsoft PCM, 16 bit, mono 24000 Hz, the streamed ones carrying exactly one RIFF header at byte 0, and every output measured as real speech rather than silence or a truncated fragment. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(llama-cpp): expose max_frames for TTS requests The Qwen3-TTS backbone does not always emit <|codec_eos_token|>, and when it does not, generation runs to upstream's 512-frame n_predict default. At the model's 12.5 Hz frame rate that is 40.96 s of audio, which a short input can trigger: one request in this session produced 40.96 s for a ten-word sentence. prepareTTSTask hardcoded n_predict to -1, so callers had no way to bound it. Add a max_frames key alongside top_k and top_p, parsed with the same strict whole-string parsing so a typo is an error rather than a silently truncated value, and rejected with a field-naming message when negative. 0 keeps the existing sentinel convention and means unset, so a request that omits it behaves exactly as before. Named max_frames rather than n_predict because frames are what the parameter means at a TTS endpoint: one frame is 0.08 s of audio. The 512-frame default is deliberately unchanged. Lowering it would truncate legitimately long inputs, which is a worse failure than an occasionally overlong one. Verified end to end on one text of thirty words: max_frames=25 HTTP 200, 96044 bytes, 2.00 s, exactly 25 frames max_frames=50 HTTP 200, 192044 bytes, 4.00 s, exactly 50 frames no max_frames HTTP 200, 572204 bytes, 11.92 s, stopped at its own codec EOS after 149 frames, unchanged behavior max_frames=-1 InvalidArgument "max_frames must be >= 0, got \"-1\"" max_frames=many InvalidArgument "max_frames must be an integer, got \"many\"" Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(llama-cpp): send the TTS sample rate up front, and tidy three review items Four items from the Task 4 review. Streaming first-byte latency. TTSStream sent the sample-rate reply only once the first audio result arrived, and a chunk needs a whole 72-frame window, roughly 5.8 s of audio and far longer in wall time on CPU. The Go side blocks on that reply before it can emit the WAV header, so a streaming client sat at zero bytes for the whole stretch. The rate is a property of the loaded model and is available synchronously from mtmd_gen_audio_get_info, so it now goes out immediately after post_task and the rate_sent bookkeeping is gone. Measured on a warm model, first byte drops from 30.48 s to 0.014 s, and the output is still a valid WAV with exactly one RIFF header at byte 0. Unchecked close. The non-streaming path ignored ofstream::close(), so a failure that only surfaces on flush was reported as success while leaving a truncated file at dst. It now returns INTERNAL like the other write failures. Wrong comment on set_lang. gen_audio::inp::get() already maps a stored blank to nullptr, so our guard is behavior-preserving, not behavior-fixing. The comment claimed otherwise; the code was right. Repetition penalty. penalty_last_n = -1 is inert at this pin, because llama_sampler_init_penalties clamps it with std::max(penalty_last_n, 0) and then builds a disabled sampler, so the 1.05 penalty never applies. Upstream's README attributes looping to a missing repeat_penalty, so it was worth testing as a root-cause fix for the model running to the frame cap. Dropping the line lets the sampling default of 64 apply, which was confirmed in the sampler chain trace as penalty_last_n = 64 with repeat_penalty = 1.050. Over 15 uncapped short requests each way it did not help: 0 of 15 ran to the cap with the penalty inert, 1 of 15 with it active. Both lines are therefore kept for parity with upstream's draft, and a comment now records that the pair is inert and why, so the next reader does not believe a penalty is applied. max_frames remains the way to bound output. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build(llama-cpp): let unpatched forks opt out of the TTS task turboquant and bonsai copy grpc-server.cpp into llama.cpp forks that do not carry our patches. disable-tts-task.sh injects the same kind of preprocessor switch disable-score-task.sh already uses, so those builds answer UNIMPLEMENTED rather than failing to compile. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(config): keep a TTS speaker-encoder projector out of vision detection Task 1 exempted a declared-TTS model's mmproj from VisionSupported, but the first real gallery entry with an mmproj still came back vision-capable through two paths the earlier fix did not close. GuessUsecases has no FLAG_VISION branch, so it falls through to true for any chat-ish model. That is not just a wrong answer at the call site: syncKnownUsecasesFromString rewrites KnownUsecaseStrings from HasUsecases, and the loader calls it more than once per config file, so the guessed FLAG_VISION is written out and parsed back into KnownUsecases as if the operator had declared it. Give GuessUsecases a FLAG_VISION branch that defers to the same explicit signals VisionSupported uses. Second, llama.cpp builds an mtmd context for the speaker-encoder projector and reports its media marker on the first chat probe, which resurrected vision after the model had been used once. Apply the same declared-TTS exemption to MediaMarker that the mmproj check already had. Verified against the qwen3-tts-llamacpp-q4 gallery entry: no vision capability and no image input modality, before load, after a TTS request, and after a chat probe. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(gallery): add Qwen3-TTS entries for the llama-cpp backend Two entries over upstream's own GGUF conversion, Q8_0 and Q4_K_M, each pairing a backbone with the Q8_0 projector. Named to sit alongside the existing qwen3-tts-cpp entries rather than replace them. Also tags the llama-cpp backend text-to-speech / TTS so the backend browser surfaces the capability. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: cover Qwen3-TTS on the llama-cpp backend Adds the gallery variants, the two-file mmproj configuration, the required voice reference, and the language and sampling knobs. Also corrects the streaming-support list, which named only voxcpm. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(config): register llama-cpp as a TTS and voice-cloning backend The branch taught the llama-cpp backend to serve Qwen3-TTS and shipped two gallery entries for it, but never told the capability table. llama-cpp still declared only the text RPCs and usecases, so: - VoiceCloningForModel returned nil at the capability check, before it ever reached the model's own tts.voice_cloning override, and /tts answered 400 "selected model does not support reference-audio voice cloning" for any localai://voice-profiles/... voice. No model YAML could opt back in. - GET /api/backends/usecases did not list tts for llama-cpp, so the gallery greyed out the TTS filter for the entries this branch adds. - The React TTS page saw voice_cloning: null and kept both models out of the Voice Library. Add the TTS RPCs and usecase, and the reference-audio contract. The contract needs narrowing, because the per-backend switch in VoiceCloningForModel ends in a permissive default: an unnarrowed entry would have advertised reference-audio cloning on every GGUF chat model in the gallery. Narrow on the declared TTS usecase rather than the model name. The TTS checkpoints are the only llama-cpp models carrying known_usecases: [tts]; name matching would have to guess at third-party repacks, and "base", the substring the neighbouring Qwen and vLLM cases key on, is a routine word in text-model names. The check reads the declared bit directly instead of going through HasUsecases, which falls through to GuessUsecases and would hand the decision to a heuristic that never had a llama.cpp TTS model in mind. DefaultUsecases stays [chat]: a bare GGUF served by llama.cpp is a chat model, and both the gallery filter and the importer read that field. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gallery): declare what nemotron-3-nano-omni actually accepts The entry is backend: vllm-omni with known_usecases: [chat, completion], no mmproj and no media marker, so it used to report vision only through the blanket GuessUsecases fallthrough that the vision branch in this branch removed. Nemotron 3 Nano Omni is a multimodal understanding model: image, video and audio in, text out. Declaring that is what the sibling vllm-omni-qwen3-omni-30b already does. known_usecases gains vision only. FLAG_VIDEO is video GENERATION, an output modality, and this model generates none; video and audio input belong in known_input_modalities, which is where AudioInputSupported and VideoInputSupported read them from. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(importers): import a Qwen3-TTS GGUF repo as TTS, not chat The llama-cpp importer hardcodes known_usecases: [chat] and assigns any mmproj-matching file as a vision projector, so ggml-org/Qwen3-TTS-12Hz-1.7B- Base-GGUF imported as a chat model with vision. Both fields were wrong, and the model was unreachable from /tts and from the Voice Library. Filenames cannot fix this. A Qwen3-TTS repo has the exact shape of a vision repo, one backbone GGUF plus one mmproj-*.gguf, so the projector's own header is the only honest signal: mtmd writes clip.has_gen_audio_encoder for the projectors it can drive as a speech pipeline and refuses to build one without it. Probe the selected mmproj for that flag, reusing the range-fetch the MTP detection already does, and declare tts when it is set. The mmproj assignment then stops reading as vision on its own, since a declared-TTS model already exempts its projector from vision detection. The probe is best-effort like the MTP one: a network blip leaves the chat default in place rather than failing the import. Verified against the real artifacts on disk: the Qwen3-TTS projector reports gen-audio, its backbone does not. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(llama-cpp): stop non-TTS models crashing on the new pin Two regressions, both hit every ordinary llama-cpp model and neither was caught locally because every test on this branch loaded a TTS model. The first is a null dereference. server_slot::tts_ctx::reset() called mtmd_helper_gen_audio_reset() unconditionally, but the gen-audio pipeline is only allocated for models carrying a gen-audio mmproj, and upstream's implementation reads ctx->pipeline before null-checking anything. Since server_slot::reset() runs during slot initialization for every model, any non-TTS model segfaulted the backend the moment it loaded. Guard the call on the is_supported() predicate already defined beside it, and keep the plain field resets unconditional. The second is unrelated to TTS and came in with the pin bump. PredictOptions.Penalty is a bare proto float, so a caller that names no repetition penalty sends 0 rather than omitting the field. Since 9de0fcf2b, common_sampler_init() rejects a non-positive penalty_repeat outright because it would divide logits by zero, turning every such request into "Failed to initialize samplers". Treat 0 as unset and leave llama.cpp's own neutral default in place. Verified with the same suite CI runs, which is what caught both: tests/e2e-backends passes 6 of 6 including the load and predict specs that were red. Qwen3-TTS still synthesises on both paths, 24 kHz mono 16-bit WAV with exactly one RIFF header on the streamed output. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
a77780ad14 |
feat(gallery): fall back to mirrors and a cached index when the primary source fails (#11389)
* feat(version): include OS and arch in the outbound User-Agent
Registries and galleries already receive LocalAI/<version>; adding the
platform follows ordinary client convention and discloses nothing a
registry cannot infer from the manifest it is asked for.
Updates the User-Agent note in docs/content/getting-started/models.md,
which documented the old format.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* feat(downloader): identify LocalAI on outbound requests
pkg/oci has always sent a User-Agent; the downloader sent none, so gallery
reads, model-file downloads, resume probes, content-length probes and the
HuggingFace safety scan all went out as a bare Go HTTP client, unattributable
to LocalAI by the hosts serving them.
HuggingFaceScan moves off the client's Get shorthand to an explicit request
for the same reason — the shorthand gives no place to hang a header.
Extends the User-Agent note in docs/content/getting-started/models.md, which
claimed the header was sent only to Ollama and OCI registries.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* feat(gallery): add a mirrors list to gallery configuration
Mirrors are an availability fallback, tried in order only after the primary
URL fails. omitempty keeps existing configurations byte-identical.
The slice makes config.Gallery non-comparable with ==, which broke the two
slices.Equal callers in the runtime settings registry. Replace them with an
explicit Gallery.Equal / GalleriesEqual so a gallery list that differs from
the baseline only by its mirrors still counts as env/CLI-set. Equal compares
the Verification block by value; == compared it by pointer identity, which
called two structurally identical policies different.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* fix(downloader): treat an HTTP error status as a failed read
ReadWithCallback handed the response body to its callback whatever the
status was, so a 404 page or a 502 from a CDN arrived as if it were a
gallery index or a model config: it parsed to nothing, got cached for an
hour, and no caller could tell the source had been down. DownloadFile has
always checked the status; this path never did.
Mirror fallback depends on it — a source that answers with an error page
has to count as unreachable, or the next candidate is never tried.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* feat(gallery): fall back to mirrors when the primary source fails
Candidates are tried primary-first with a bounded timeout each, and a
source that just failed is skipped for a cooldown so a dead host is not
re-dialled on every listing. When every candidate is in cooldown they are
all tried anyway: refusing to serve a gallery we might be able to reach is
worse than one slow request.
The one-hour index cache is untouched and stays keyed on the gallery's own
identity, so a mirror-served fetch fills the entry the primary would have.
No SSRF validation is applied to the candidates. validateGalleryConfigURL
guards GetGalleryConfigFromURL because that URL arrives in a request body;
mirrors come from the operator's gallery configuration, the same place the
primary has always come from, and the index fetch has never validated the
primary. Validating mirrors while the primary goes unchecked would buy
nothing and would break the deployment mirrors exist for — an index served
from a host on the LAN.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* fix(gallery): loosen the mirror fetch timeout and stop blaming the caller
The downloader only ever bounded response headers, never the body, so the
per-attempt deadline added with mirror fallback was the first whole-transfer
timeout this path has had. At 30s the default 2.2 MB index demanded ~75 KB/s
sustained: a rural-DSL, mobile or satellite user who used to wait 60s and
succeed would now fail, and then eat a 10-minute cooldown on a source that
was perfectly healthy. Raised to 120s (~19 KB/s), which no link that could
go on to download a model will miss, and made it a var so a test can shorten
it and prove a hanging candidate is actually abandoned.
Caller cancellation is no longer recorded as a failure of the source.
Unreachable today since getGalleryElements passes context.Background(), but
once a request context is wired through, a browser disconnect would have
blackholed every candidate for ten minutes over something the sources had
no part in.
Also document that mirrors do not cover a .ref gallery URL: the reference is
resolved before mirrors are considered, so a .ref that cannot be fetched
fails the gallery outright. Routing .ref resolution through the candidate
list needs a per-candidate resolve-and-fetch and a decision about cache
identity, which is more than this change should carry.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* feat(gallery): serve the last known good index when everything is offline
A successful fetch is cached alongside the models directory and served when
no source is reachable, so an offline or airgapped machine can still list
its gallery. Entries may be stale in that state, and the fallback is logged.
The copy is deliberately kept out of the models directory, where a <name>.yaml
file is read as an installed model's configuration, and is named after a digest
of the gallery URL so the model and backend galleries cannot collide. Writing
it is best effort: a read-only or full disk must not fail a fetch that
otherwise succeeded.
Also corrects the mirror scheme list in the docs: the HuggingFace prefixes are
huggingface://, hf:// and hf.co/, not huggingface:.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* fix(gallery): only cache a response that is really a gallery index
The last known good copy was written on any 2xx, before anything looked
at the bytes: the parse only happens later, in getGalleryElements. A
captive portal, a corporate proxy or a CDN error page all answer HTTP 200
with HTML, so any of them could overwrite a good copy. The listing fails
then and there, and the next offline start — the one case this cache
exists for — serves the interception page instead of the gallery it
already had.
Probe the body before persisting it: unmarshal into a []any and keep the
older copy unless the result is a non-empty sequence. An empty document
is rejected too. It parses fine, so a parse-only check would still let a
blank response replace a populated index with one that lists nothing,
which from the user's side is the same outage; and an empty index is
worth nothing offline, so there is no case where caching it beats keeping
what came before. The live body is still returned to the caller — the
probe gates persistence only, and getGalleryElements remains the thing
that reports a real parse failure.
Also in this pass:
- The empty-basePath guard only caught exact "". galleryCachePath(".")
and galleryCachePath("models") still resolved the cache sibling against
the process working directory, which is what the guard was written to
prevent. Reject any non-absolute base.
- The docs claimed the offline cache "applies to every gallery, with or
without mirrors". Not true for a .ref URL: the reference is resolved
before the cache is consulted, so a .ref gallery fails offline even
after a successful earlier fetch, and the cache file it writes can
never be read. Extend the .ref warning and qualify the sentence.
- pkg/oci's UserAgent comment never mentioned the platform component
added earlier on this branch.
- resetGalleryFailures and expireGalleryFailure had no non-test callers;
move them into the test file.
- The all-candidates-failed error reported len(attempt), so a three
mirror gallery with two sources in cooldown said "all 1 source(s)
failed" — which reads as a misconfiguration. Report how many were
configured and how many were skipped.
- Give the package's tests their own TMPDIR. The cache is a sibling of
the models directory, which is right in production, but specs that
build a models directory directly under /tmp made the sibling resolve
to /tmp/cache and left it behind after every run.
Assisted-by: Claude:claude-opus-5 [go vet] [go test]
* fix(gallery): convert the new tests to Ginkgo and clear the lint gate
.agents/coding-style.md requires Ginkgo v2 + Gomega for every Go test and
has forbidigo enforce it; the stdlib-style tests still in the tree are tech
debt, not a pattern. Every test file this branch added was written in the
forbidden style, which is what turned CI red.
Convert all five of them. internal had no suite bootstrap, so add one;
core/config, core/gallery and pkg/downloader already have theirs and are
reused, so no package mixes styles. pkg/downloader/useragent_test.go and
read_status_test.go were not in CI's forbidigo list but used the same
forbidden calls, so they are converted too.
The one conversion with a trap in it is core/gallery. Go's t.TempDir()
yields $TMPDIR/<TestName>NNNN/001, so the gallery cache — a sibling of the
models directory — was isolated per test. GinkgoT().TempDir() yields a flat
$TMPDIR/ginkgoNNNN, which would put every spec's cache in one shared
directory and break the specs that count files in it. tempModelsDir()
restores the original isolation.
Also make the deliberate cleanup-path ignores explicit with `_ =`, drop the
gallery cache directory to 0750 (nothing outside the server's own user and
group reads it), and justify the cache read with a #nosec G304 comment in
the form already used elsewhere in the tree: the path is a hex sha256 under
a fixed directory with a non-absolute base already rejected, so no
caller-supplied text reaches it.
Re-ran the mutations these specs were verified against — dropping the
platform suffix from UserAgent, making Gallery.Equal ignore Mirrors and
ignore Name, removing persistGalleryIndex's validity probe, removing the
!filepath.IsAbs guard, not skipping a cooled-down candidate, and dropping
the per-attempt timeout. All seven still fail the converted specs.
Assisted-by: Claude:claude-opus-5 [go vet] [go test] [golangci-lint] [gosec]
---------
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
ea438cdeaf |
feat(vllm-cpp): wire the full engine config surface through engine_args (#11159)
The backend could configure four of the engine's knobs (block size, KV block
count, max sequence length, max concurrent sequences) out of a config surface
that is considerably larger. Speculative decoding, prefix caching, the
chunked-prefill token budget, the scheduling policy and the external KV
connector were reachable from vllm.cpp's own HTTP server and from nothing
LocalAI could write in a model config.
Config now goes through `engine_args:`, the same map the vLLM and SGLang
backends take, with keys spelled as vLLM's own CLI flags so a speculative_config
or kv_transfer_config block written for vLLM works verbatim. The legacy
`options:` list keeps working and reads every key too; engine_args wins where
both set one. Unknown keys are logged and ignored rather than fatal: the field
is shared with the other engines, so a config carrying their knobs must not take
the model down.
Two details worth knowing:
`enable_prefix_caching: false` maps to the ABI tri-state force-OFF (2), not 0.
0 means "let the model capability decide" and dense architectures default the
cache on, so collapsing the two would silently enable it against an explicit
false. enable_jump_forward (ABI v10) shares the encoding, deferring to
VT_ENABLE_JUMP_FORWARD instead of to the model.
The importer probes config.json on a vllm-cpp import and writes
speculative_config: {method: mtp} when the checkpoint declares an MTP head, the
safetensors analogue of the llama-cpp importer's GGUF probe. DFlash draft repos
are refused with a warning instead, since a drafter cannot serve alone and the
pairing is not derivable from either repo. The draft path is resolved against
LocalAI's model directory, because the engine only looks in a directory holding
config.json or in the HF cache and never downloads: the repo-id spelling the
vLLM docs teach used to die deep in the load with "draft checkpoint not found".
docs/content/features/text-generation.md gains a vllm.cpp section covering the
engine_args table, all three speculative methods, LMCache and the legacy list.
The backend had no documentation page before.
This replaces a branch that had gone stale behind master and carried its own
route to ABI v10, which #11386 has since landed in minimal form. Rebased onto
that as a single commit rather than replaying the intermediate steps, whose
ABI v9 mirrors no longer make sense against master's pin. The Darwin build
fixes for Apple Clang's gnu-folding-constant diagnostic on C++, Objective-C and
Objective-C++, originally authored by localai-org-maint-bot, are folded in here.
Verified: `make abi-check` agrees at v10; unit specs, core/config and
core/gallery/importers green; and the full e2e passes in 1330s against a CPU
libvllm.so reporting ABI v10 with Qwen_Qwen3.5-0.8B-Q4_K_M.gguf (load, blocking
completion, streaming, chat and tool calls).
Assisted-by: Claude:claude-fable-5 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
Richard Palethorpe
|
f8d3f31594 |
fix(vram): contain malformed GGUF metadata (#11374)
Recover parser panics at metadata boundaries, skip unneeded remote arrays, and use the parser's overflow-hardened release. Keep detached gallery workers and CrispASR probes from terminating their processes on malformed GGUF input. Disable startup warming in the provided Compose files as an operational fallback. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> |