The workflow policy forbade the quay credential names in the add-on package
workflow, so the login that now uses them failed the policy test on master.
The add-on pipeline logs in with the same registry credentials as the
backend builds, so those names are allowed. The test that rejected them is
removed.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The add-on publish read ADDON_OCI_USERNAME and ADDON_OCI_PASSWORD, which are
not set, so the publish failed at login with 'Username and password
required'. Point it at the quayUsername and quayPassword secrets the backend
and image workflows already use.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
⬆️ Checksum updates in the model library
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
The settings page spec hard-coded 58 fields. Each new setting broke it,
most recently max_concurrent_backend_operations, which made the page
list 59. Compare the grouped keys with the schema keys instead, so a
failure names the field that is in no group or shown twice. Add the
new setting to the mocked settings payload.
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update leejet/stable-diffusion.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(sd): adopt owning generation results
The sd.cpp bump replaces raw image and video outputs with owning results.
Adapt image generation, video generation and upscaling to the new API.
Use upstream destructors to release all pixels, audio and metadata.
Add model-free native checks for result ownership and failure paths.
Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The document scrolled again on the gallery. The screen-reader spans in
the table rows are position: absolute, and nothing above them was
positioned, so they resolved against the viewport, escaped the table
scroller and the pinned shell, and stretched the document to about twice
the window height. Make the table scroller and the full-height page the
containing block, so the spans are clipped with the rows.
The tabs and filters were also packed tight. Raise the view tabs to 40px
with an accent underline on the current one, space the facet chips and
toggles apart, give toggles, chips, density and state segments a hit area
of at least 36px (40 to 44px on phones), and leave more air between the
filter rows. Existing --dk-* tokens only.
Add a spec that checks the document height equals the window height
while the table still overflows.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The add-on cards, the Find add-ons tab and the install dialog said
"Adds a page" for a library entry but nothing about chat tools, so the
tools only showed once the add-on was installed.
The library index now carries toolCount and tools on each entry, with
the same names as the installed view. They come from capabilities.tools
of the manifest; admin tools are not chat tools and are not counted.
Tools is capped at 32 names and toolCount stays the full number. The
catalog reader validates the hint and refuses it on a backend entry.
addonpkg catalog writes the fields. The new catalog-tools subcommand adds
them to an existing index from addons/<id>/manifest.json, and leaves
every digest and artifact as it was.
The UI reads the fields through the same helper as the installed view and
shows "Adds N tools" when N is above zero.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* chore(parakeet-cpp): bump parakeet.cpp to load Phonon-2.5 models
Move the pin to the current parakeet.cpp master. It includes the
dense and packed CPU paths for the Phonon-2.5 checkpoints, which the
previous pin cannot load.
After the bump, run `make purge` in backend/go/parakeet-cpp so the
next build clones the new revision.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
* feat(gallery): add Phonon-2.5 parakeet-cpp models
Add the multilingual Phonon-2.5 (25 European languages) and the
English-only Phonon-2.5-English checkpoints as parakeet-cpp entries.
Each comes in four builds: F16, Q8_0, Q4_K and packed. The packed
build runs on the CPU only. The files are in
mudler/parakeet-cpp-gguf, pinned by SHA-256. The weights are
CC-BY-4.0.
The entries need the parakeet.cpp pin from the previous commit.
Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
---------
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The two UD-Q4_K_XL and UD-Q6_K_XL download URLs added for the LFM2.5
dynamic variants pointed at a repository revision that does not exist,
so both returned 404. Pin them to the current repository revision. The
files at that revision carry the sha256 values already in the entries.
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add the IQ3_S GGUF build with both shards and its vision projector.
Pin all downloads and document the installation command.
Assisted-by: Codex:GPT-6
(cherry picked from commit 15ed1cb4e1, mudler/LocalAI#12860)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add pinned Q4_K_M and Q8_0 builds with linked variants and install docs.
Regenerate the gallery from the model library and fix its stale header.
Assisted-by: Codex:gpt-6
(cherry picked from commit 6b2e8ea09c, mudler/LocalAI#12857)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add official Q4_K_M and Q8_0 builds for memory-writing workflows.
Use the embedded template with no-think mode and pinned downloads.
Document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit a1259642c5, mudler/LocalAI#12851)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer the official Q4_K_M and Q8_0 builds with their vision projector.
Pin artifact revisions and document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 9f98baa8e5, mudler/LocalAI#12833)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add IQ4_XS and Q8_0 MAX builds with pinned downloads and linked variants.
Use the embedded chat template and document installation.
Assisted-by: Codex:gpt-6
(cherry picked from commit 94b54e009a, mudler/LocalAI#12831)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add three GGUF quantizations with a shared vision projector and pinned
artifact URLs. Document installation and the default context size.
Assisted-by: Codex:gpt-6
(cherry picked from commit c8df4d6fef, mudler/LocalAI#12823)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add the publisher Q4_K_M and Q8_0 builds with pinned downloads and
verified SHA256 hashes. Document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 64d0b3b094, mudler/LocalAI#12821)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Use the published mmproj filename for both uncensored Q4 and Q8 entries.
The old filename returns 404, preventing model installation.
Preserve the local projector path and existing checksum.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit 80b0708da4, mudler/LocalAI#12820)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add IQ4_XS and Q6_K_P builds with pinned weights and linked variants.
Document installation and the text-only, ordinary-decoding defaults.
Assisted-by: Codex:gpt-6
(cherry picked from commit 1c5eea9580, mudler/LocalAI#12819)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add pinned UD-Q4_K_XL and Q8_0 builds with the vision projector and installation documentation.
Assisted-by: Codex:gpt-6
(cherry picked from commit 31978a28ef, mudler/LocalAI#12809)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Unsloth dynamic Q4 and Q6 builds alongside the official GGUFs.
Pin their revisions and verify hashes through two Hugging Face sources.
Assisted-by: Codex:gpt-6
(cherry picked from commit ab8d685f01, mudler/LocalAI#12774)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add PQ2_0, PTQ1_0, and Q2_0 builds with the Q8_0 vision projector.
Pin files to the publisher revision and document variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 7270bdc508, mudler/LocalAI#12773)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add three GGUF packings with the Q8_0 vision projector and document
installation. Pin asset revisions and verify hashes against HF metadata
and download headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit 77f1ab29c8, mudler/LocalAI#12771)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Fix the existing NVFP4 variant to use its downloaded BF16 projector.
Assisted-by: Codex:GPT-6 [shell]
(cherry picked from commit 3bfed3b8a0, mudler/LocalAI#12769)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer three GGUF builds and a safetensors build for English retrieval.
Pin model files and document the retrieval query prefix.
Assisted-by: Codex:gpt-6
(cherry picked from commit 02413e8190, mudler/LocalAI#12722)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add F16, Q8_0 and Q4_K_M builds with CLS pooling and retrieval usage documentation. Pin the GGUF revision and verify SHA256 values against Hugging Face metadata and download headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit e61c44f317, mudler/LocalAI#12717)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add F16, Q8_0 and Q4_K_M builds for English retrieval. Pin the source
revision and verify each SHA256 against HF metadata and download headers.
Document query prefixes and the 512-token context.
Assisted-by: Codex:gpt-6
(cherry picked from commit b99b669cef, mudler/LocalAI#12713)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add text-only Q4 and Q5 builds for llama.cpp with pinned downloads.
Group the builds as variants and document their supported capabilities.
Assisted-by: Codex:gpt-6
(cherry picked from commit c7cbe18a62, mudler/LocalAI#12707)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M, Q6_K, and Q8_0 builds for llama.cpp with pinned assets.
Group the builds and document installation, reasoning, and tool setup.
Assisted-by: Codex:gpt-6
(cherry picked from commit f9e7f0bfbe, mudler/LocalAI#12706)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add AtomicChat MiniCPM-V 4.7 35B-A3B Q4 and Q6 builds for llama.cpp.
Include every weight shard and the F16 vision projector.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit eff464d58a, mudler/LocalAI#12690)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Kujira's mixed IQ2 Saluki fine-tune for llama.cpp with plain and MTP
decoding. Pin the weights and document the text-only entries.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit 24f23a66aa, mudler/LocalAI#12688)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4 and IQ4 GGUF builds with a BF16 vision projector and pinned
Hugging Face downloads. Keep the original release available.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit 9c9e18450e, mudler/LocalAI#12670)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Maya S, S24, M, and L builds through the existing GLM group.
Pin all weight shards and the vision projector to an HF revision.
Document the standard llama.cpp configuration and its limits.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit 4aab47ba66, mudler/LocalAI#12666)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer the Saluki IQ2 weights with an MTP head for llama.cpp. Pin both
assets and document how to select the variant.
Assisted-by: Codex:GPT-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
(cherry picked from commit c745b96781, mudler/LocalAI#12662)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update ggml-org/llama.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(llama-cpp): adapt to the multimodal rerank signature
Upstream llama.cpp added query_files and doc_files parameters to
format_prompt_rerank() (ggml-org/llama.cpp#29625). The gRPC rerank
call passed the init options in their place, so grpc-server.cpp no
longer compiled against the new pin.
prepare.sh now probes server-common.h for query_files and writes
LOCALAI_HAS_RERANK_FILES into llama_compat.h. When it is set, the
rerank call passes two empty media lists. The rerank API is text
only, so behaviour is unchanged. Forks that still use the old
signature (turboquant, bonsai) compile as before.
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The chat settings sheet, the Talk session sheet and the agent and task
preview sheets set up their focus handling in an effect that depended on
onClose. Every parent passes onClose as an inline arrow, so each re-render
of the page gave it a new identity: the effect cleanup sent focus back to
the opener and the effect ran again and focused the Close button.
Any edit in a sheet re-renders the page, so focus left the control being
used. In the chat sheet, typing in the system prompt moved focus to Close
after the first key, and a following space activated Close and dismissed
the sheet; an open native dropdown in the sheet closed by itself.
Keep the latest onClose in a ref and run the focus effect once per open.
Escape still calls the current onClose; initial focus on Close, the Tab
trap and restoring focus to the opener are unchanged.
The e2e specs type key by key (or switch preview tabs) and assert that
focus stays put; they fail without this change.
Docs-Not-Needed: bug fix, no user-facing behaviour change beyond the fix
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 773cae7259)
Agent jobs (/api/agent/jobs, local and on distributed agent workers) run
cogito against a LocalAI client that sends no max_tokens of its own, so
every completion gets the client's fixed default of 16384. max_iterations
bounds the number of turns and loop_detection repeated tool calls, but
neither stops one completion that keeps generating, and 16384 is the same
for a small tool-picking model and a reasoning model that thinks at length.
Add agent.max_generation_tokens to the model config. When set, both job
paths apply it to the client with SetMaxTokens; requests that carry their
own cap still win, so cogito's length retry can raise it. Unset keeps
today's behaviour.
The specs run each job path against an MCP fixture and a recording LLM
endpoint and check the max_tokens the completions carry; they fail when
either call site drops the cap.
Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
(cherry picked from commit 5600a1cabe)
The vLLM and SGLang backends no longer stop at 200 tokens when a request
has no max_tokens. Generation is now bounded by the context window.
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
- ApplyReasoningEffort keeps an operator's reasoning.disable for high, xhigh and max
- sglang: _configured_budget() feeds the strict-thinking warning; tested with
effort_budgets alone
Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
(cherry picked from commit 45a960ca1f)
- warn on an effort_budgets entry without a token count (high=)
- update comments: enable_thinking=false still wins over a listed level
- document that precedence in text-generation.md
- cover xhigh/max and the empty-entry warning in the tests
Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
(cherry picked from commit 0bd723a652)
