Only load files whose real extension is .yaml or .yml so backup files like model.yaml.bak do not override active configs. Add a regression test covering plain and timestamped backup files.
Assisted-by: Codex:gpt-5.4 docker
Signed-off-by: leinasi2014 <leinasi2014@gmail.com>
When installing a backend with a custom OCI URI in distributed mode,
the URI was captured in ManagementOp.ExternalURI by the HTTP handler
but never forwarded to workers. BackendInstallRequest had no URI field,
so workers fell through to the gallery lookup and failed with
"no backend found with name <custom-name>".
Add URI/Name/Alias fields to BackendInstallRequest and thread them from
ManagementOp through DistributedBackendManager.InstallBackend() and the
RemoteUnloaderAdapter. On the worker side, route to InstallExternalBackend
when URI is set instead of InstallBackendFromGallery. Update all
remaining InstallBackend call sites (UpgradeBackend, reconciler
pending-op drain, router auto-install) to pass empty strings for the
new params.
Assisted-by: Claude Code:claude-sonnet-4-6
Signed-off-by: Russell Sim <rsl@simopolis.xyz>
The API Traces tab in /app/traces always showed (0) traces despite requests
being recorded.
The /api/traces endpoint was registered in both localai.go and ui_api.go.
The ui_api.go version wrapped the response as {"traces": [...]} instead of
the flat []APIExchange array that both the React UI (Traces.jsx) and the
legacy Alpine.js UI (traces.html) expect. Because Echo matched the ui_api.go
handler, Array.isArray(apiData) always returned false, making the API Traces
tab permanently empty.
Remove the duplicate endpoints from ui_api.go so only the correct flat-array
version in localai.go is served.
Also use mime.ParseMediaType for the Content-Type check in the trace
middleware so requests with parameters (e.g. application/json; charset=utf-8)
are still traced.
Signed-off-by: Pawel Brzozowski <paul@ontux.net>
Co-authored-by: Pawel Brzozowski <paul@ontux.net>
GET /api/settings returns settings.ApiKeys as the merged env+runtime list
via ApplicationConfig.ToRuntimeSettings(). The WebUI displays that list and
round-trips it back on POST /api/settings unchanged.
UpdateSettingsEndpoint was then doing:
appConfig.ApiKeys = append(envKeys, runtimeKeys...)
where runtimeKeys already contained envKeys (because the UI got them from
the merged GET). Every save therefore duplicated the env keys on top of
the previous merge, and also wrote the duplicates to runtime_settings.json
so the duplication survived restarts and compounded with each save. This
is the user-visible behaviour in #9071: the Web UI shows the keys
twice / three times after consecutive saves.
Before we marshal the settings to disk or call ApplyRuntimeSettings, drop
any incoming key that already appears in startupConfig.ApiKeys. The file
on disk now stores only the genuinely runtime-added keys; the subsequent
append(envKeys, runtimeKeys...) produces one copy of each env key, as
intended. Behaviour is unchanged for users who never had env keys set.
Fixes#9071
Co-authored-by: SAY-5 <SAY-5@users.noreply.github.com>
Two interrelated bugs that combined to make a meta backend impossible
to uninstall once its concrete had been removed from disk (partial
install, earlier crash, manual cleanup).
1. DeleteBackendFromSystem returned "meta backend %q not found" and
bailed out early when the concrete directory didn't exist,
preventing the orphaned meta dir from ever being removed. Treat a
missing concrete as idempotent success — log a warning and continue
to remove the orphan meta.
2. InstallBackendFromGallery's "already installed, skip" short-circuit
only checked that the name was known (`backends.Exists(name)`); an
orphaned meta whose RunFile points at a missing concrete still
satisfies that check, so every reinstall returned nil without doing
anything. Afterwards the worker's findBackend returned empty and we
kept looping with "backend %q not found after install attempt".
Require the entry to be actually runnable (run.sh stat-able, not a
directory) before skipping.
New helper isBackendRunnable centralises the runnability test so both
the install guard and future callers stay in sync. Tests cover the
orphaned-meta delete path and the non-runnable short-circuit case.
pending_backend_ops rows targeting agent-type workers looped forever:
the reconciler fan-out hit a NATS subject the worker doesn't subscribe
to, returned ErrNoResponders, we marked the node unhealthy, and the
health monitor flipped it back to healthy on the next heartbeat. Next
tick, same row, same failure.
Three related fixes:
1. enqueueAndDrainBackendOp skips nodes whose NodeType != backend.
Agent workers handle agent NATS subjects, not backend.install /
delete / list, so enqueueing for them guarantees an infinite retry
loop. Silent skip is correct — they aren't consumers of these ops.
2. Reconciler drain mirrors enqueueAndDrainBackendOp's behavior on
nats.ErrNoResponders: mark the node unhealthy before recording the
failure, so subsequent ListDuePendingBackendOps (filters by
status=healthy) stops picking the row until the node actually
recovers. Matches the synchronous fan-out path.
3. Dead-letter cap at maxPendingBackendOpAttempts (10). After ~1h of
exponential backoff the row is a poison message; further retries
just thrash NATS. Row is deleted and logged at ERROR so it stays
visible without staying infinite.
Plus a one-shot startup cleanup in NewNodeRegistry: drop queue rows
that target agent-type nodes, non-existent nodes, or carry an empty
backend name. Guarded by the same schema-migration advisory lock so
only one instance performs it. The guards above prevent new rows of
this shape; this closes the migration gap for existing ones.
Tests: the prune migration (valid row stays, agent + empty-name rows
drop) on top of existing upsert / backoff coverage.
* fix(distributed): detect backend upgrades across worker nodes
Before this change `DistributedBackendManager.CheckUpgrades` delegated to the
local manager, which read backends from the frontend filesystem. In
distributed deployments the frontend has no backends installed locally —
they live on workers — so the upgrade-detection loop never ran and the UI
silently never surfaced upgrades even when the gallery advertised newer
versions or digests.
Worker-side: NATS backend.list reply now carries Version, URI and Digest
for each installed backend (read from metadata.json).
Frontend-side: DistributedBackendManager.ListBackends aggregates per-node
refs (name, status, version, digest) instead of deduping, and CheckUpgrades
feeds that aggregation into gallery.CheckUpgradesAgainst — a new entrypoint
factored out of CheckBackendUpgrades so both paths share the same core
logic.
Cluster drift policy: when per-node version/digest tuples disagree, the
backend is flagged upgradeable regardless of whether any single node
matches the gallery, and UpgradeInfo.NodeDrift enumerates the outliers so
operators can see *why* it is out of sync. The next upgrade-all realigns
the cluster.
Tests cover: drift detection, unanimous-match (no upgrade), and the
empty-installed-version path that the old distributed code silently
missed.
* feat(ui): surface backend upgrades in the System page
The System page (Manage.jsx) only showed updates as a tiny inline arrow,
so operators routinely missed them. Port the Backend Gallery's upgrade UX
so System speaks the same visual language:
- Yellow banner at the top of the Backends tab when upgrades are pending,
with an "Upgrade all" button (serial fan-out, matches the gallery) and a
"Updates only" filter toggle.
- Warning pill (↑ N) next to the tab label so the count is glanceable even
when the banner is scrolled out of view.
- Per-row labeled "Upgrade to vX.Y" button (replaces the icon-only button
that silently flipped semantics between Reinstall and Upgrade), plus an
"Update available" badge in the new Version column.
- New columns: Version (with upgrade + drift chips), Nodes (per-node
attribution badges for distributed mode, degrading to a compact
"on N nodes · M offline" chip above three nodes), Installed (relative
time).
- System backends render a "Protected" chip instead of a bare "—" so rows
still align and the reason is obvious.
- Delete uses the softer btn-danger-ghost so rows don't scream red; the
ConfirmDialog still owns the "are you sure".
The upgrade checker also needed the same per-worker fix as the previous
commit: NewUpgradeChecker now takes a BackendManager getter so its
periodic runs call the distributed CheckUpgrades (which asks workers)
instead of the empty frontend filesystem. Without this the /api/backends/
upgrades endpoint stayed empty in distributed mode even with the protocol
change in place.
New CSS primitives — .upgrade-banner, .tab-pill, .badge-row, .cell-stack,
.cell-mono, .cell-muted, .row-actions, .btn-danger-ghost — all live in
App.css so other pages can adopt them without duplicating styles.
* feat(ui): polish the Nodes page so it reads like a product
The Nodes page was the biggest visual liability in distributed mode.
Rework the main dashboard surfaces in place without changing behavior:
StatCards: uniform height (96px min), left accent bar colored by the
metric's semantic (success/warning/error/primary), icon lives in a
36x36 soft-tinted chip top-right, value is left-aligned and large.
Grid auto-fills so the row doesn't collapse on narrow viewports. This
replaces the previous thin-bordered boxes with inconsistent heights.
Table rows: expandable rows now show a chevron cue on the left (rotates
on expand) so users know rows open. Status cell became a dedicated chip
with an LED-style halo dot instead of a bare bullet. Action buttons gained
labels — "Approve", "Resume", "Drain" — so the icons aren't doing all
the semantic work; the destructive remove action uses the softer
btn-danger-ghost variant so rows don't scream red, with the ConfirmDialog
still owning the real "are you sure". Applied cell-mono/cell-muted
utility classes so label chips and addresses share one spacing/font
grammar instead of re-declaring inline styles everywhere.
Expanded drawer: empty states for Loaded Models and Installed Backends
now render as a proper drawer-empty card (dashed border, icon, one-line
hint) instead of a plain muted string that read like broken formatting.
Tabs: three inline-styled buttons became the shared .tab class so they
inherit focus ring, hover state, and the rest of the design system —
matches the System page.
"Add more workers" toggle turned into a .nodes-add-worker dashed-border
button labelled "Register a new worker" (action voice) instead of a
chevron + muted link that operators kept mistaking for broken text.
New shared CSS primitives carry over to other pages:
.stat-grid + .stat-card, .row-chevron, .node-status, .drawer-empty,
.nodes-add-worker.
* feat(distributed): durable backend fan-out + state reconciliation
Two connected problems handled together:
1) Backend delete/install/upgrade used to silently skip non-healthy nodes,
so a delete during an outage left a zombie on the offline node once it
returned. The fan-out now records intent in a new pending_backend_ops
table before attempting the NATS round-trip. Currently-healthy nodes
get an immediate attempt; everyone else is queued. Unique index on
(node_id, backend, op) means reissuing the same operation refreshes
next_retry_at instead of stacking duplicates.
2) Loaded-model state could drift from reality: a worker OOM'd, got
killed, or restarted a backend process would leave a node_models row
claiming the model was still loaded, feeding ghost entries into the
/api/nodes/models listing and the router's scheduling decisions.
The existing ReplicaReconciler gains two new passes that run under a
fresh KeyStateReconciler advisory lock (non-blocking, so one wedged
frontend doesn't freeze the cluster):
- drainPendingBackendOps: retries queued ops whose next_retry_at has
passed on currently-healthy nodes. Success deletes the row; failure
bumps attempts and pushes next_retry_at out with exponential backoff
(30s → 15m cap). ErrNoResponders also marks the node unhealthy.
- probeLoadedModels: gRPC-HealthChecks addresses the DB thinks are
loaded but hasn't seen touched in the last probeStaleAfter (2m).
Unreachable addresses are removed from the registry. A pluggable
ModelProber lets tests substitute a fake without standing up gRPC.
DistributedBackendManager exposes DeleteBackendDetailed so the HTTP
handler can surface per-node outcomes ("2 succeeded, 1 queued") to the
UI in a follow-up commit; the existing DeleteBackend still returns
error-only for callers that don't care about node breakdown.
Multi-frontend safety: the state pass uses advisorylock.TryWithLockCtx
on a new key so N frontends coordinate — the same pattern the health
monitor and replica reconciler already rely on. Single-node mode runs
both passes inline (adapter is nil, state drain is a no-op).
Tests cover the upsert semantics, backoff math, the probe removing an
unreachable model but keeping a reachable one, and filtering by
probeStaleAfter.
* feat(ui): show cluster distribution of models in the System page
When a frontend restarted in distributed mode, models that workers had
already loaded weren't visible until the operator clicked into each node
manually — the /api/models/capabilities endpoint only knew about
configs on the frontend's filesystem, not the registry-backed truth.
/api/models/capabilities now joins in ListAllLoadedModels() when the
registry is active, returning loaded_on[] with node id/name/state/status
for each model. Models that live in the registry but lack a local config
(the actual ghosts, not recovered from the frontend's file cache) still
surface with source="registry-only" so operators can see and persist
them; without that emission they'd be invisible to this frontend.
Manage → Models replaces the old Running/Idle pill with a distribution
cell that lists the first three nodes the model is loaded on as chips
colored by state (green loaded, blue loading, amber anything else). On
wider clusters the remaining count collapses into a +N chip with a
title-attribute breakdown. Disabled / single-node behavior unchanged.
Adopted models get an extra "Adopted" ghost-icon chip with hover copy
explaining what it means and how to make it permanent.
Distributed mode also enables a 10s auto-refresh and a "Last synced Xs
ago" indicator next to the Update button so ghost rows drop off within
one reconcile tick after their owning process dies. Non-distributed
mode is untouched — no polling, no cell-stack, same old Running/Idle.
* feat(ui): NodeDistributionChip — shared per-node attribution component
Large clusters were going to break the Manage → Backends Nodes column:
the old inline logic rendered every node as a badge and would shred the
layout at >10 workers, plus the Manage → Models distribution cell had
copy-pasted its own slightly-different version.
NodeDistributionChip handles any cluster size with two render modes:
- small (≤3 nodes): inline chips of node names, colored by health.
- large: a single "on N nodes · M offline · K drift" summary chip;
clicking opens a Popover with a per-node table (name, status,
version, digest for backends; name, status, state for models).
Drift counting mirrors the backend's summarizeNodeDrift so the UI
number matches UpgradeInfo.NodeDrift. Digests are truncated to the
docker-style 12-char form with the full value preserved in the title.
Popover is a new general-purpose primitive: fixed positioning anchored
to the trigger, flips above when there's no room below, closes on
outside-click or Escape, returns focus to the trigger. Uses .card as
its surface so theming is inherited. Also useful for a future
labels-editor popup and the user menu.
Manage.jsx drops its duplicated inline Nodes-column + loaded_on cell
and uses the shared chip with context="backends" / "models"
respectively. Delete code removes ~40 lines of ad-hoc logic.
* feat(ui): shared FilterBar across the System page tabs
The Backends gallery had a nice search + chip + toggle strip; the System
page had nothing, so the two surfaces felt like different apps. Lift the
pattern into a reusable FilterBar and wire both System tabs through it.
New component core/http/react-ui/src/components/FilterBar.jsx renders a
search input, a role="tablist" chip row (aria-selected for a11y), and
optional toggles / right slot. Chips support an optional `count` which
the System page uses to show "User 3", "Updates 1" etc.
System Models tab: search by id or backend; chips for
All/Running/Idle/Disabled/Pinned plus a conditional Distributed chip in
distributed mode. "Last synced" + Update button live in the right slot.
System Backends tab: search by name/alias/meta-backend-for; chips for
All/User/System/Meta plus conditional Updates / Offline-nodes chips
when relevant. The old ad-hoc "Updates only" toggle from the upgrade
banner folded into the Updates chip — one source of truth for that
filter. Offline chip only appears in distributed mode when at least
one backend has an unhealthy node, so the chip row stays quiet on
healthy clusters.
Filter state persists in URL query params (mq/mf/bq/bf) so deep links
and tab switches keep the operator's filter context instead of
resetting every time.
Also adds an "Adopted" distribution path: when a model in
/api/models/capabilities carries source="registry-only" (discovered on
a worker but not configured locally), the Models tab shows a ghost chip
labelled "Adopted" with hover copy explaining how to persist it — this
is what closes the loop on the ghost-model story end-to-end.
Upstream llama.cpp (PR #21962) switched the server-side mtmd media
marker to a random per-server string and removed the legacy
"<__media__>" backward-compat replacement in mtmd_tokenizer. The
Go layer still emitted the hardcoded "<__media__>", so on the
non-tokenizer-template path the prompt arrived with a marker mtmd
did not recognize and tokenization failed with "number of bitmaps
(1) does not match number of markers (0)".
Report the active media marker via ModelMetadataResponse.media_marker
and substitute the sentinel "<__media__>" with it right before the
gRPC call, after the backend has been loaded and probed. Also skip
the Go-side multimodal templating entirely when UseTokenizerTemplate
is true — llama.cpp's oaicompat_chat_params_parse already injects its
own marker and StringContent is unused in that path. Backends that do
not expose the field keep the legacy "<__media__>" behavior.
Editing a model's YAML and changing the `name:` field previously wrote
the new body to the original `<oldName>.yaml`. On reload the config
loader indexed that file under the new name while the old key
lingered in memory, producing two entries in the system UI that
shared a single underlying file — deleting either removed both.
Detect the rename in EditModelEndpoint and rename the on-disk
`<name>.yaml` and `._gallery_<name>.yaml` to match, drop the stale
in-memory key before the reload, and redirect the editor URL in the
React UI so it tracks the new name. Reject conflicts (409) and names
containing path separators (400).
Fixes#9294
* feat(backends): add sglang
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(sglang): force AVX-512 CXXFLAGS and disable CI e2e job
sgl-kernel's shm.cpp uses __m512 AVX-512 intrinsics unconditionally;
-march=native fails on CI runners without AVX-512 in /proc/cpuinfo.
Force -march=sapphirerapids so the build always succeeds, matching
sglang upstream's docker/xeon.Dockerfile recipe.
The resulting binary still requires an AVX-512 capable CPU at runtime,
so disable tests-sglang-grpc in test-extra.yml for the same reason
tests-vllm-grpc is disabled. Local runs with make test-extra-backend-sglang
still work on hosts with the right SIMD baseline.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(sglang): patch CMakeLists.txt instead of CXXFLAGS for AVX-512
CXXFLAGS with -march=sapphirerapids was being overridden by
add_compile_options(-march=native) in sglang's CPU CMakeLists.txt,
since CMake appends those flags after CXXFLAGS. Sed-patch the
CMakeLists.txt directly after cloning to replace -march=native.
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Bumps LocalAGI to pick up the LocalRecall postgres backend fix that
resizes the pgvector column when the configured embedding model
returns vectors of a different dimensionality than the existing
collection. Switching the agent pool's embedding model now triggers
a transparent re-embed at startup instead of failing every subsequent
upload with 'expected N dimensions, not M' (SQLSTATE 22000).
Also surfaces a 409 with an actionable message in
UploadToCollectionEndpoint as a safety net for the rare cases the
upstream migration path doesn't cover (e.g. a model swapped at
runtime), instead of the previous opaque 500.
* refactor(backends): extract python_utils + add mlx_utils shared helpers
Move parse_options() and messages_to_dicts() out of vllm_utils.py into a
new framework-agnostic python_utils.py, and re-export them from vllm_utils
so existing vllm / vllm-omni imports keep working.
Add mlx_utils.py with split_reasoning() and parse_tool_calls() — ported
from mlx_vlm/server.py's process_tool_calls. These work with any
mlx-lm / mlx-vlm tool module (anything exposing tool_call_start,
tool_call_end, parse_tool_call). Used by the mlx and mlx-vlm backends in
later commits to emit structured ChatDelta.tool_calls without
reimplementing per-model parsing.
Shared smoke tests confirm:
- parse_options round-trips bool/int/float/string
- vllm_utils re-exports are identity-equal to python_utils originals
- mlx_utils parse_tool_calls handles <tool_call>...</tool_call> with a
shim module and produces a correctly-indexed list with JSON arguments
- mlx_utils split_reasoning extracts <think> blocks and leaves clean
content
* feat(mlx): wire native tool parsers + ChatDelta + token usage + logprobs
Bring the MLX backend up to the same structured-output contract as vLLM
and llama.cpp: emit Reply.chat_deltas so the OpenAI HTTP layer sees
tool_calls and reasoning_content, not just raw text.
Key insight: mlx_lm.load() returns a TokenizerWrapper that already auto-
detects the right tool parser from the model's chat template
(_infer_tool_parser in mlx_lm/tokenizer_utils.py). The wrapper exposes
has_tool_calling, has_thinking, tool_parser, tool_call_start,
tool_call_end, think_start, think_end — no user configuration needed,
unlike vLLM.
Changes in backend/python/mlx/backend.py:
- Imports: replace inline parse_options / messages_to_dicts with the
shared helpers from python_utils. Pull split_reasoning / parse_tool_calls
from the new mlx_utils shared module.
- LoadModel: log the auto-detected has_tool_calling / has_thinking /
tool_parser_type for observability. Drop the local is_float / is_int
duplicates.
- _prepare_prompt: run request.Messages through messages_to_dicts so
tool_call_id / tool_calls / reasoning_content survive the conversion,
and pass tools=json.loads(request.Tools) + enable_thinking=True (when
request.Metadata says so) to apply_chat_template. Falls back on
TypeError for tokenizers whose template doesn't accept those kwargs.
- _build_generation_params: return an additional (logits_params,
stop_words) pair. Maps RepetitionPenalty / PresencePenalty /
FrequencyPenalty to mlx_lm.sample_utils.make_logits_processors and
threads StopPrompts through to post-decode truncation.
- New _tool_module_from_tokenizer / _finalize_output / _truncate_at_stop
helpers. _finalize_output runs split_reasoning when has_thinking is
true and parse_tool_calls (using a SimpleNamespace shim around the
wrapper's tool_parser callable) when has_tool_calling is true, then
extracts prompt_tokens, generation_tokens and (best-effort) logprobs
from the last GenerationResponse chunk.
- Predict: use make_logits_processors, accumulate text + last_response,
finalize into a structured Reply carrying chat_deltas,
prompt_tokens, tokens, logprobs. Early-stops on user stop sequences.
- PredictStream: per-chunk Reply still carries raw message bytes for
back-compat but now also emits chat_deltas=[ChatDelta(content=delta)].
On loop exit, emit a terminal Reply with structured
reasoning_content / tool_calls / token counts / logprobs — so the Go
side sees tool calls without needing the regex fallback.
- TokenizeString RPC: uses the TokenizerWrapper's encode(); returns
length + tokens or FAILED_PRECONDITION if the model isn't loaded.
- Free RPC: drops model / tokenizer / lru_cache, runs gc.collect(),
calls mx.metal.clear_cache() when available, and best-effort clears
torch.cuda as a belt-and-suspenders.
* feat(mlx-vlm): mirror MLX parity (tool parsers + ChatDelta + samplers)
Same treatment as the MLX backend: emit structured Reply.chat_deltas,
tool_calls, reasoning_content, token counts and logprobs, and extend
sampling parameter coverage beyond the temp/top_p pair the backend
used to handle.
- Imports: drop the inline is_float/is_int helpers, pull parse_options /
messages_to_dicts from python_utils and split_reasoning /
parse_tool_calls from mlx_utils. Also import make_sampler and
make_logits_processors from mlx_lm.sample_utils — mlx-vlm re-uses them.
- LoadModel: use parse_options; call mlx_vlm.tool_parsers._infer_tool_parser
/ load_tool_module to auto-detect a tool module from the processor's
chat_template. Stash think_start / think_end / has_thinking so later
finalisation can split reasoning blocks without duck-typing on each
call. Logs the detected parser type.
- _prepare_prompt: convert proto Messages via messages_to_dicts (so
tool_call_id / tool_calls survive), pass tools=json.loads(request.Tools)
and enable_thinking=True to apply_chat_template when present, fall
back on TypeError for older mlx-vlm versions. Also handle the
prompt-only + media and empty-prompt + media paths consistently.
- _build_generation_params: return (max_tokens, sampler_params,
logits_params, stop_words). Maps repetition_penalty / presence_penalty /
frequency_penalty and passes them through make_logits_processors.
- _finalize_output / _truncate_at_stop: common helper used by Predict
and PredictStream to split reasoning, run parse_tool_calls against the
auto-detected tool module, build ToolCallDelta list, and extract token
counts + logprobs from the last GenerationResult.
- Predict / PredictStream: switch from mlx_vlm.generate to mlx_vlm.stream_generate
in both paths, accumulate text + last_response, pass sampler and
logits_processors through, emit content-only ChatDelta per streaming
chunk followed by a terminal Reply carrying reasoning_content,
tool_calls, prompt_tokens, tokens and logprobs. Non-streaming Predict
returns the same structured Reply shape.
- New helper _collect_media extracted from the duplicated base64 image /
audio decode loop.
- New TokenizeString RPC using the processor's tokenizer.encode and
Free RPC that drops model/processor/config, runs gc + Metal cache
clear + best-effort torch.cuda cache clear.
* feat(importer/mlx): auto-set tool_parser/reasoning_parser on import
Mirror what core/gallery/importers/vllm.go does: after applying the
shared inference defaults, look up the model URI in parser_defaults.json
and append matching tool_parser:/reasoning_parser: entries to Options.
The MLX backends auto-detect tool parsers from the chat template at
runtime so they don't actually consume these options — but surfacing
them in the generated YAML:
- keeps the import experience consistent with vllm
- gives users a single visible place to override
- documents the intended parser for a given model family
* test(mlx): add helper unit tests + TokenizeString/Free + e2e make targets
- backend/python/mlx/test.py: add TestSharedHelpers with server-less
unit tests for parse_options, messages_to_dicts, split_reasoning and
parse_tool_calls (using a SimpleNamespace shim to fake a tool module
without requiring a model). Plus test_tokenize_string and test_free
RPC tests that load a tiny MLX-quantized Llama and exercise the new
RPCs end-to-end.
- backend/python/mlx-vlm/test.py: same helper unit tests + cleanup of
the duplicated import block at the top of the file.
- Makefile: register BACKEND_MLX and BACKEND_MLX_VLM (they were missing
from the docker-build-target eval list — only mlx-distributed had a
generated target before). Add test-extra-backend-mlx and
test-extra-backend-mlx-vlm convenience targets that build the
respective image and run tests/e2e-backends with the tools capability
against mlx-community/Qwen2.5-0.5B-Instruct-4bit. The MLX backend
auto-detects the tool parser from the chat template so no
BACKEND_TEST_OPTIONS is needed (unlike vllm).
* fix(libbackend): don't pass --copies to venv unless PORTABLE_PYTHON=true
backend/python/common/libbackend.sh:ensureVenv() always invoked
'python -m venv --copies', but macOS system python (and some other
builds) refuses with:
Error: This build of python cannot create venvs without using symlinks
--copies only matters when _makeVenvPortable later relocates the venv,
which only happens when PORTABLE_PYTHON=true. Make --copies conditional
on that flag and fall back to default (symlinked) venv otherwise.
Caught while bringing up the mlx backend on Apple Silicon — the same
build path is used by every Python backend with USE_PIP=true.
* fix(mlx): support mlx-lm 0.29.x tool calling + drop deprecated clear_cache
The released mlx-lm 0.29.x ships a much simpler tool-calling API than
HEAD: TokenizerWrapper detects the <tool_call>...</tool_call> markers
from the tokenizer vocab and exposes has_tool_calling /
tool_call_start / tool_call_end, but does NOT expose a tool_parser
callable on the wrapper and does NOT ship a mlx_lm.tool_parsers
subpackage at all (those only exist on main).
Caught while running the smoke test on Apple Silicon with the
released mlx-lm 0.29.1: tokenizer.tool_parser raised AttributeError
(falling through to the underlying HF tokenizer), so
_tool_module_from_tokenizer always returned None and tool calls slipped
through as raw <tool_call>...</tool_call> text in Reply.message instead
of being parsed into ChatDelta.tool_calls.
Fix: when has_tool_calling is True but tokenizer.tool_parser is missing,
default the parse_tool_call callable to json.loads(body.strip()) — that's
exactly what mlx_lm.tool_parsers.json_tools.parse_tool_call does on HEAD
and covers the only format 0.29 detects (<tool_call>JSON</tool_call>).
Future mlx-lm releases that ship more parsers will be picked up
automatically via the tokenizer.tool_parser attribute when present.
Also tighten the LoadModel logging — the old log line read
init_kwargs.get('tool_parser_type') which doesn't exist on 0.29 and
showed None even when has_tool_calling was True. Log the actual
tool_call_start / tool_call_end markers instead.
While here, switch Free()'s Metal cache clear from the deprecated
mx.metal.clear_cache to mx.clear_cache (mlx >= 0.30), with a
fallback for older releases. Mirrored to the mlx-vlm backend.
* feat(mlx-distributed): mirror MLX parity (tool calls + ChatDelta + sampler)
Same treatment as the mlx and mlx-vlm backends: emit Reply.chat_deltas
with structured tool_calls / reasoning_content / token counts /
logprobs, expand sampling parameter coverage beyond temp+top_p, and
add the missing TokenizeString and Free RPCs.
Notes specific to mlx-distributed:
- Rank 0 is the only rank that owns a sampler — workers participate in
the pipeline-parallel forward pass via mx.distributed and don't
re-implement sampling. So the new logits_params (repetition_penalty,
presence_penalty, frequency_penalty) and stop_words apply on rank 0
only; we don't need to extend coordinator.broadcast_generation_params,
which still ships only max_tokens / temperature / top_p to workers
(everything else is a rank-0 concern).
- Free() now broadcasts CMD_SHUTDOWN to workers when a coordinator is
active, so they release the model on their end too. The constant is
already defined and handled by the existing worker loop in
backend.py:633 (CMD_SHUTDOWN = -1).
- Drop the locally-defined is_float / is_int / parse_options trio in
favor of python_utils.parse_options, re-exported under the module
name for back-compat with anything that imported it directly.
- _prepare_prompt: route through messages_to_dicts so tool_call_id /
tool_calls / reasoning_content survive, pass tools=json.loads(
request.Tools) and enable_thinking=True to apply_chat_template, fall
back on TypeError for templates that don't accept those kwargs.
- New _tool_module_from_tokenizer (with the json.loads fallback for
mlx-lm 0.29.x), _finalize_output, _truncate_at_stop helpers — same
contract as the mlx backend.
- LoadModel logs the auto-detected has_tool_calling / has_thinking /
tool_call_start / tool_call_end so users can see what the wrapper
picked up for the loaded model.
- backend/python/mlx-distributed/test.py: add the same TestSharedHelpers
unit tests (parse_options, messages_to_dicts, split_reasoning,
parse_tool_calls) that exist for mlx and mlx-vlm.
* fix(schema): serialize ToolCallID and Reasoning in Messages.ToProto
The ToProto conversion was dropping tool_call_id and reasoning_content
even though both proto and Go fields existed, breaking multi-turn tool
calling and reasoning passthrough to backends.
* refactor(config): introduce backend hook system and migrate llama-cpp defaults
Adds RegisterBackendHook/runBackendHooks so each backend can register
default-filling functions that run during ModelConfig.SetDefaults().
Migrates the existing GGUF guessing logic into hooks_llamacpp.go,
registered for both 'llama-cpp' and the empty backend (auto-detect).
Removes the old guesser.go shim.
* feat(config): add vLLM parser defaults hook and importer auto-detection
Introduces parser_defaults.json mapping model families to vLLM
tool_parser/reasoning_parser names, with longest-pattern-first matching.
The vllmDefaults hook auto-fills tool_parser and reasoning_parser
options at load time for known families, while the VLLMImporter writes
the same values into generated YAML so users can review and edit them.
Adds tests covering MatchParserDefaults, hook registration via
SetDefaults, and the user-override behavior.
* feat(vllm): wire native tool/reasoning parsers + chat deltas + logprobs
- Use vLLM's ToolParserManager/ReasoningParserManager to extract structured
output (tool calls, reasoning content) instead of reimplementing parsing
- Convert proto Messages to dicts and pass tools to apply_chat_template
- Emit ChatDelta with content/reasoning_content/tool_calls in Reply
- Extract prompt_tokens, completion_tokens, and logprobs from output
- Replace boolean GuidedDecoding with proper GuidedDecodingParams from Grammar
- Add TokenizeString and Free RPC methods
- Fix missing `time` import used by load_video()
* feat(vllm): CPU support + shared utils + vllm-omni feature parity
- Split vllm install per acceleration: move generic `vllm` out of
requirements-after.txt into per-profile after files (cublas12, hipblas,
intel) and add CPU wheel URL for cpu-after.txt
- requirements-cpu.txt now pulls torch==2.7.0+cpu from PyTorch CPU index
- backend/index.yaml: register cpu-vllm / cpu-vllm-development variants
- New backend/python/common/vllm_utils.py: shared parse_options,
messages_to_dicts, setup_parsers helpers (used by both vllm backends)
- vllm-omni: replace hardcoded chat template with tokenizer.apply_chat_template,
wire native parsers via shared utils, emit ChatDelta with token counts,
add TokenizeString and Free RPCs, detect CPU and set VLLM_TARGET_DEVICE
- Add test_cpu_inference.py: standalone script to validate CPU build with
a small model (Qwen2.5-0.5B-Instruct)
* fix(vllm): CPU build compatibility with vllm 0.14.1
Validated end-to-end on CPU with Qwen2.5-0.5B-Instruct (LoadModel, Predict,
TokenizeString, Free all working).
- requirements-cpu-after.txt: pin vllm to 0.14.1+cpu (pre-built wheel from
GitHub releases) for x86_64 and aarch64. vllm 0.14.1 is the newest CPU
wheel whose torch dependency resolves against published PyTorch builds
(torch==2.9.1+cpu). Later vllm CPU wheels currently require
torch==2.10.0+cpu which is only available on the PyTorch test channel
with incompatible torchvision.
- requirements-cpu.txt: bump torch to 2.9.1+cpu, add torchvision/torchaudio
so uv resolves them consistently from the PyTorch CPU index.
- install.sh: add --index-strategy=unsafe-best-match for CPU builds so uv
can mix the PyTorch index and PyPI for transitive deps (matches the
existing intel profile behaviour).
- backend.py LoadModel: vllm >= 0.14 removed AsyncLLMEngine.get_model_config
so the old code path errored out with AttributeError on model load.
Switch to the new get_tokenizer()/tokenizer accessor with a fallback
to building the tokenizer directly from request.Model.
* fix(vllm): tool parser constructor compat + e2e tool calling test
Concrete vLLM tool parsers override the abstract base's __init__ and
drop the tools kwarg (e.g. Hermes2ProToolParser only takes tokenizer).
Instantiating with tools= raised TypeError which was silently caught,
leaving chat_deltas.tool_calls empty.
Retry the constructor without the tools kwarg on TypeError — tools
aren't required by these parsers since extract_tool_calls finds tool
syntax in the raw model output directly.
Validated with Qwen/Qwen2.5-0.5B-Instruct + hermes parser on CPU:
the backend correctly returns ToolCallDelta{name='get_weather',
arguments='{"location": "Paris, France"}'} in ChatDelta.
test_tool_calls.py is a standalone smoke test that spawns the gRPC
backend, sends a chat completion with tools, and asserts the response
contains a structured tool call.
* ci(backend): build cpu-vllm container image
Add the cpu-vllm variant to the backend container build matrix so the
image registered in backend/index.yaml (cpu-vllm / cpu-vllm-development)
is actually produced by CI.
Follows the same pattern as the other CPU python backends
(cpu-diffusers, cpu-chatterbox, etc.) with build-type='' and no CUDA.
backend_pr.yml auto-picks this up via its matrix filter from backend.yml.
* test(e2e-backends): add tools capability + HF model name support
Extends tests/e2e-backends to cover backends that:
- Resolve HuggingFace model ids natively (vllm, vllm-omni) instead of
loading a local file: BACKEND_TEST_MODEL_NAME is passed verbatim as
ModelOptions.Model with no download/ModelFile.
- Parse tool calls into ChatDelta.tool_calls: new "tools" capability
sends a Predict with a get_weather function definition and asserts
the Reply contains a matching ToolCallDelta. Uses UseTokenizerTemplate
with OpenAI-style Messages so the backend can wire tools into the
model's chat template.
- Need backend-specific Options[]: BACKEND_TEST_OPTIONS lets a test set
e.g. "tool_parser:hermes,reasoning_parser:qwen3" at LoadModel time.
Adds make target test-extra-backend-vllm that:
- docker-build-vllm
- loads Qwen/Qwen2.5-0.5B-Instruct
- runs health,load,predict,stream,tools with tool_parser:hermes
Drops backend/python/vllm/test_{cpu_inference,tool_calls}.py — those
standalone scripts were scaffolding used while bringing up the Python
backend; the e2e-backends harness now covers the same ground uniformly
alongside llama-cpp and ik-llama-cpp.
* ci(test-extra): run vllm e2e tests on CPU
Adds tests-vllm-grpc to the test-extra workflow, mirroring the
llama-cpp and ik-llama-cpp gRPC jobs. Triggers when files under
backend/python/vllm/ change (or on run-all), builds the local-ai
vllm container image, and runs the tests/e2e-backends harness with
BACKEND_TEST_MODEL_NAME=Qwen/Qwen2.5-0.5B-Instruct, tool_parser:hermes,
and the tools capability enabled.
Uses ubuntu-latest (no GPU) — vllm runs on CPU via the cpu-vllm
wheel we pinned in requirements-cpu-after.txt. Frees disk space
before the build since the docker image + torch + vllm wheel is
sizeable.
* fix(vllm): build from source on CI to avoid SIGILL on prebuilt wheel
The prebuilt vllm 0.14.1+cpu wheel from GitHub releases is compiled with
SIMD instructions (AVX-512 VNNI/BF16 or AMX-BF16) that not every CPU
supports. GitHub Actions ubuntu-latest runners SIGILL when vllm spawns
the model_executor.models.registry subprocess for introspection, so
LoadModel never reaches the actual inference path.
- install.sh: when FROM_SOURCE=true on a CPU build, temporarily hide
requirements-cpu-after.txt so installRequirements installs the base
deps + torch CPU without pulling the prebuilt wheel, then clone vllm
and compile it with VLLM_TARGET_DEVICE=cpu. The resulting binaries
target the host's actual CPU.
- backend/Dockerfile.python: accept a FROM_SOURCE build-arg and expose
it as an ENV so install.sh sees it during `make`.
- Makefile docker-build-backend: forward FROM_SOURCE as --build-arg
when set, so backends that need source builds can opt in.
- Makefile test-extra-backend-vllm: call docker-build-vllm via a
recursive $(MAKE) invocation so FROM_SOURCE flows through.
- .github/workflows/test-extra.yml: set FROM_SOURCE=true on the
tests-vllm-grpc job. Slower but reliable — the prebuilt wheel only
works on hosts that share the build-time SIMD baseline.
Answers 'did you test locally?': yes, end-to-end on my local machine
with the prebuilt wheel (CPU supports AVX-512 VNNI). The CI runner CPU
gap was not covered locally — this commit plugs that gap.
* ci(vllm): use bigger-runner instead of source build
The prebuilt vllm 0.14.1+cpu wheel requires SIMD instructions (AVX-512
VNNI/BF16) that stock ubuntu-latest GitHub runners don't support —
vllm.model_executor.models.registry SIGILLs on import during LoadModel.
Source compilation works but takes 30-40 minutes per CI run, which is
too slow for an e2e smoke test. Instead, switch tests-vllm-grpc to the
bigger-runner self-hosted label (already used by backend.yml for the
llama-cpp CUDA build) — that hardware has the required SIMD baseline
and the prebuilt wheel runs cleanly.
FROM_SOURCE=true is kept as an opt-in escape hatch:
- install.sh still has the CPU source-build path for hosts that need it
- backend/Dockerfile.python still declares the ARG + ENV
- Makefile docker-build-backend still forwards the build-arg when set
Default CI path uses the fast prebuilt wheel; source build can be
re-enabled by exporting FROM_SOURCE=true in the environment.
* ci(vllm): install make + build deps on bigger-runner
bigger-runner is a bare self-hosted runner used by backend.yml for
docker image builds — it has docker but not the usual ubuntu-latest
toolchain. The make-based test target needs make, build-essential
(cgo in 'go test'), and curl/unzip (the Makefile protoc target
downloads protoc from github releases).
protoc-gen-go and protoc-gen-go-grpc come via 'go install' in the
install-go-tools target, which setup-go makes possible.
* ci(vllm): install libnuma1 + libgomp1 on bigger-runner
The vllm 0.14.1+cpu wheel ships a _C C++ extension that dlopens
libnuma.so.1 at import time. When the runner host doesn't have it,
the extension silently fails to register its torch ops, so
EngineCore crashes on init_device with:
AttributeError: '_OpNamespace' '_C_utils' object has no attribute
'init_cpu_threads_env'
Also add libgomp1 (OpenMP runtime, used by torch CPU kernels) to be
safe on stripped-down runners.
* feat(vllm): bundle libnuma/libgomp via package.sh
The vllm CPU wheel ships a _C extension that dlopens libnuma.so.1 at
import time; torch's CPU kernels in turn use libgomp.so.1 (OpenMP).
Without these on the host, vllm._C silently fails to register its
torch ops and EngineCore crashes with:
AttributeError: '_OpNamespace' '_C_utils' object has no attribute
'init_cpu_threads_env'
Rather than asking every user to install libnuma1/libgomp1 on their
host (or every LocalAI base image to ship them), bundle them into
the backend image itself — same pattern fish-speech and the GPU libs
already use. libbackend.sh adds ${EDIR}/lib to LD_LIBRARY_PATH at
run time so the bundled copies are picked up automatically.
- backend/python/vllm/package.sh (new): copies libnuma.so.1 and
libgomp.so.1 from the builder's multilib paths into ${BACKEND}/lib,
preserving soname symlinks. Runs during Dockerfile.python's
'Run backend-specific packaging' step (which already invokes
package.sh if present).
- backend/Dockerfile.python: install libnuma1 + libgomp1 in the
builder stage so package.sh has something to copy (the Ubuntu
base image otherwise only has libgomp in the gcc dep chain).
- test-extra.yml: drop the workaround that installed these libs on
the runner host — with the backend image self-contained, the
runner no longer needs them, and the test now exercises the
packaging path end-to-end the way a production host would.
* ci(vllm): disable tests-vllm-grpc job (heterogeneous runners)
Both ubuntu-latest and bigger-runner have inconsistent CPU baselines:
some instances support the AVX-512 VNNI/BF16 instructions the prebuilt
vllm 0.14.1+cpu wheel was compiled with, others SIGILL on import of
vllm.model_executor.models.registry. The libnuma packaging fix doesn't
help when the wheel itself can't be loaded.
FROM_SOURCE=true compiles vllm against the actual host CPU and works
everywhere, but takes 30-50 minutes per run — too slow for a smoke
test on every PR.
Comment out the job for now. The test itself is intact and passes
locally; run it via 'make test-extra-backend-vllm' on a host with the
required SIMD baseline. Re-enable when:
- we have a self-hosted runner label with guaranteed AVX-512 VNNI/BF16, or
- vllm publishes a CPU wheel with a wider baseline, or
- we set up a docker layer cache that makes FROM_SOURCE acceptable
The detect-changes vllm output, the test harness changes (tests/
e2e-backends + tools cap), the make target (test-extra-backend-vllm),
the package.sh and the Dockerfile/install.sh plumbing all stay in
place.
* feat: add PreferDevelopmentBackends setting, expose isMeta/isDevelopment in API
- Add PreferDevelopmentBackends config field, CLI flag, runtime setting
- Add IsDevelopment() method to GalleryBackend
- Use AvailableBackendsUnfiltered in UI API to show all backends
- Expose isMeta, isDevelopment, preferDevelopmentBackends in backend API response
* feat: upgrade banner with Upgrade All button, detect pre-existing backends
- Add upgrade banner on Backends page showing count and Upgrade All button
- Fix upgrade detection for backends installed before version tracking:
flag as upgradeable when gallery has a version but installed has none
- Fix OCI digest check to flag backends with no stored digest as upgradeable
* feat: add backend versioning data model foundation
Add Version, URI, and Digest fields to BackendMetadata for tracking
installed backend versions and enabling upgrade detection. Add Version
field to GalleryBackend. Add UpgradeAvailable/AvailableVersion fields
to SystemBackend. Implement GetImageDigest() for lightweight OCI digest
lookups via remote.Head. Record version, URI, and digest at install time
in InstallBackend() and propagate version through meta backends.
* feat: add backend upgrade detection and execution logic
Add CheckBackendUpgrades() to compare installed backend versions/digests
against gallery entries, and UpgradeBackend() to perform atomic upgrades
with backup-based rollback on failure. Includes Agent A's data model
changes (Version/URI/Digest fields, GetImageDigest).
* feat: add AutoUpgradeBackends config and runtime settings
Add configuration and runtime settings for backend auto-upgrade:
- RuntimeSettings field for dynamic config via API/JSON
- ApplicationConfig field, option func, and roundtrip conversion
- CLI flag with LOCALAI_AUTO_UPGRADE_BACKENDS env var
- Config file watcher support for runtime_settings.json
- Tests for ToRuntimeSettings, ApplyRuntimeSettings, and roundtrip
* feat(ui): add backend version display and upgrade support
- Add upgrade check/trigger API endpoints to config and api module
- Backends page: version badge, upgrade indicator, upgrade button
- Manage page: version in metadata, context-aware upgrade/reinstall button
- Settings page: auto-upgrade backends toggle
* feat: add upgrade checker service, API endpoints, and CLI command
- UpgradeChecker background service: checks every 6h, auto-upgrades when enabled
- API endpoints: GET /backends/upgrades, POST /backends/upgrades/check, POST /backends/upgrade/:name
- CLI: `localai backends upgrade` command, version display in `backends list`
- BackendManager interface: add UpgradeBackend and CheckUpgrades methods
- Wire upgrade op through GalleryService backend handler
- Distributed mode: fan-out upgrade to worker nodes via NATS
* fix: use advisory lock for upgrade checker in distributed mode
In distributed mode with multiple frontend instances, use PostgreSQL
advisory lock (KeyBackendUpgradeCheck) so only one instance runs
periodic upgrade checks and auto-upgrades. Prevents duplicate
upgrade operations across replicas.
Standalone mode is unchanged (simple ticker loop).
* test: add e2e tests for backend upgrade API
- Test GET /api/backends/upgrades returns 200 (even with no upgrade checker)
- Test POST /api/backends/upgrade/:name accepts request and returns job ID
- Test full upgrade flow: trigger upgrade via API, wait for job completion,
verify run.sh updated to v2 and metadata.json has version 2.0.0
- Test POST /api/backends/upgrades/check returns 200
- Fix nil check for applicationInstance in upgrade API routes
* feat: add toggle mechanism to enable/disable models from loading on demand
Implements #9303 - Adds ability to disable models from being auto-loaded
while keeping them in the collection.
Backend changes:
- Add Disabled field to ModelConfig struct with IsDisabled() getter
- New ToggleModelEndpoint handler (PUT /models/toggle/:name/:action)
- Request middleware returns 403 when disabled model is requested
- Capabilities endpoint exposes disabled status
Frontend changes:
- Toggle switch in System > Models table Actions column
- Visual indicators: dimmed row, red Disabled badge, muted icons
- Tooltip describes toggle function on hover
- Loading state while API call is in progress
* fix: remove extra closing brace causing syntax error in request middleware
* refactor: reorder Actions column - Stop button before toggle switch
* refactor: migrate from toggle to toggle-state per PR review feedback
When TASK_RESPONSE_TYPE_OAI_CHAT is used, the first streaming token
produces a JSON array with two elements: a role-init chunk and the
actual content chunk. The grpc-server loop called attach_chat_deltas
for both elements with the same raw_result pointer, stamping the first
token's ChatDelta.Content on both replies. The Go side accumulated both,
emitting the first content token twice to SSE clients.
Fix: in the array iteration loops in PredictStream, detect role-init
elements (delta has "role" key) and skip attach_chat_deltas for them.
Only content/reasoning elements get chat deltas attached.
Reasoning models are unaffected because their first token goes into
reasoning_content, not content.
The Go-side incremental JSON parser was emitting the same tool call on
every streaming token because it lacked the len > lastEmittedCount guard
that the XML parser had. On top of that, the post-streaming default:
case re-emitted all tool calls from index 0, duplicating everything.
This produced duplicate delta.tool_calls events causing clients to
accumulate arguments as "{args}{args}" — invalid JSON.
Fixes:
- JSON incremental parser: add len(jsonResults) > lastEmittedCount guard
and loop from lastEmittedCount (matching the XML parser pattern)
- Post-streaming default: case: skip i < lastEmittedCount entries that
were already emitted during streaming
- JSON parser: use blocking channel send (matching XML parser behavior)
When clients like Nextcloud or Home Assistant send requests with tools
to thinking models (e.g. Gemma 4 with <|channel>thought tags), the
response was empty despite the backend producing valid content.
Root cause: the C++ autoparser puts clean content in both the raw
Response and ChatDeltas. The Go-side PrependThinkingTokenIfNeeded
then prepends the thinking start token to the already-clean content,
causing ExtractReasoning to classify the entire response as unclosed
reasoning. This made cbRawResult empty, triggering a retry loop that
never succeeds.
Two fixes:
- inference.go: check ChatDeltas for content/tool_calls regardless of
whether Response is empty, so skipCallerRetry fires correctly
- chat.go: when ChatDeltas have content but no tool calls, use that
content directly instead of falling back to the empty cbRawResult
This changeset makes visible when files are being staged, so users are
aware that the model "isn't ready yet" for requests.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(ui): Add dynamic model editor with autocomplete
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(docs): Add link to longformat installation video
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
We were not checking against the api keys when db == nil.
This commit also cleanups now unused middleware
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(chat): do not retry if we had chatdeltas or tooldeltas from backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: use oai compat for llama.cpp
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: apply to non-streaming path too
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* map also other fields
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The C++ PEG parser needs a few tokens to identify the reasoning format
(e.g. "<|channel>thought\n" for Gemma 4). During this warm-up, the gRPC
layer was sending raw partial tag tokens to Go, which leaked into the
reasoning field.
- Clear reply.message in gRPC when autoparser is active but has no diffs
yet, matching llama.cpp server behavior of only emitting classified output
- Prefer C++ autoparser chat deltas for reasoning/content in all streaming
paths, falling back to Go-side extraction for backends without autoparser
(e.g. vLLM)
- Override non-streaming no-tools result with chat delta content when available
- Guard PrependThinkingTokenIfNeeded against partial tag prefixes during
streaming accumulation
- Reorder default thinking tokens so <|channel>thought is checked before
<|think|> (Gemma 4 templates contain both)
