mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 09:08:54 -04:00
master
93
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 mudler-agentandEttore Di Giacinto
|
7c74d26555 |
feat(addons): run the add-on owner as its own workload (#12867)
* feat(addons): generate and load a static carrier key set A split deployment needs the owner and the frontends to share certificates and a signing key that outlive a process. The loopback carrier makes fresh keys at every start, so it cannot serve that. GenerateCarrierKeys writes a CA certificate, an owner leaf and a frontend leaf, and the frontend signing key pair. It drops the CA key, so nobody can issue a third leaf, and it refuses to overwrite any file. LoadCarrierConfig reads only the files of one role and refuses key files that group or other users can access. The owner never forwards, but NewCarrier still requires a signing key, so the owner config gets a throwaway key in memory instead of the frontends' private key. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): add util addons-carrier-keys An operator who runs the add-on owner and its frontends as separate workloads needs a way to make the shared key set. The command wraps GenerateCarrierKeys: --out names the directory and --owner-host, which can repeat, sets the names the owner certificate is valid for. It prints which files belong on the owner and which on the frontends. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): add the owner and frontend roles to local-ai run Every local-ai run process is its own add-on owner, so a distributed deployment cannot scale its frontends: replicas that share a data volume fight over the owner lock. --addons-role selects combined (today's behaviour, the default), owner or frontend. The owner and frontend roles also take --addons-owner-address and --addons-carrier-dir, and the owner takes --addons-owner-listen. They use the fixed carrier identities and the key set from the carrier key directory. The frontend role has no add-on root, so it never creates the add-ons folder. A bad role setup stops startup with a message that names the flag. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): keep the frontend role away from owner state A frontend holds no add-on state, but it still wrote the library sources file of the data path, which is the owner's file. The frontend role now skips the library option and reads only the galleries named by the flags, and logs a warning when it has no account database, because its pins are then kept per frontend. The add-on manager rejects a relative root even for a forwarding frontend, so the frontend config names the absolute path where an owner would keep its state. Nothing creates or opens it, and a spec checks that the data path stays empty. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(addons): run the owner and frontends as separate applications The split roles are only useful if an owner and its frontends work as separate processes that share nothing but the carrier keys and the owner address. A spec now builds them as separate Application values with their own data paths and keys from GenerateCarrierKeys. It covers a frontend that lists apps and reads add-on status through the owner, two frontends on one key set, a frontend that starts while the owner is down and answers unavailable, a second owner refused on the same root, and an owner that restarts on the same root and address and still serves the installed add-on to the same frontend. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(addons): describe running the owner as its own workload An operator who runs several frontend replicas had no documented way to stop each one from being its own add-on owner. The add-ons page now has a section for the owner and frontend roles: one owner replica with its own volume and a recreate-style rollout, a stable owner address, key generation and per-role mounts, a Compose example, what a restart and an owner outage look like, the models-path limit, and the frontend limits. The singleton section names the roles and the distributed-state mode, and the distributed mode page links to the new section. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): gate the addons feature in /api/features One function, Application.AddonsFeature, decides whether the add-on side is on. A combined or owner process answers true when add-ons are enabled and the owner manager exists. A frontend answers true when the owner answered the carrier's audience call within 2 s, and keeps that answer for 10 s so /api/features does not dial the owner per request. /api/features reports the result as "addons", and fine_tuning and quantization take the same value, because both are add-ons. The frontend cache is per-instance state. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): answer 503 on every add-on route when add-ons are off With --addons-enabled=false the real add-on, fine-tuning and quantization routes and services are not registered. One catch-all per prefix answers the typed unavailable response of an absent owner, for any path under it, so a client cannot tell which routes exist. The response is the one the gateway already writes (gateway.WriteUnavailable over typedError), not a second format. With add-ons on, the same routes sit behind RequireAddonsFeature, which reads Application.AddonsFeature, so a frontend that cannot reach the owner gives the same answer. The per-user feature middleware still runs after the gate. No endpoint is added, so the swagger, /api/instructions and RouteFeatureRegistry surfaces do not change. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): build no carrier for a frontend with add-ons off addonConfigFor already returned the zero config before it read a role flag when add-ons are disabled. Say so on the way out: when a role, owner address, listen address or carrier directory flag is set, log one info line that the flags are ignored. A frontend with --addons-enabled=false needs no owner address and no key directory, loads no keys and builds no carrier. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): hide add-on entries when the addons feature is off The UI reads features.addons from /api/features. When it is false: the sidebar shows no Add-ons entry and no pinned apps, the 404 page lists no add-on destination, the shell does not call /api/addons/pins or /api/addons/builtin, and /app/addons, /app/addons/*, /app/fine-tune and /app/quantize lead back to /app. The Build hub tabs for add-ons, fine-tuning and quantization were already keyed on features and now follow the gate. An absent key (an older server) counts as on. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(addons): describe the addons feature gate The --addons-enabled row now says the UI hides the add-on entries and every add-on, fine-tuning and quantization route answers 503. A new subsection describes the addons key of /api/features, the 10 s frontend cache as per-instance state, and that a frontend with add-ons off needs no owner address or key directory. The fine-tuning and quantization pages say they are off with --addons-enabled=false. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(addons): give a frontend no add-on state root OwnerConfig.validate required an absolute root for every role, so a frontend named a path under the data directory that nothing was allowed to open. Only the owner has a state root now: validate checks it when the instance is the owner, and the frontend role leaves Root empty. Nothing on a frontend reads or creates it. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(addons): make the carrier signing key optional for the owner NewCarrier required an Ed25519 signing key of every instance, so the owner role loaded a throwaway key in memory that it never used. The owner never signs an outbound request, so it now needs none: NewCarrier accepts an empty key when the instance is the owner and still requires a whole key from a frontend, and a malformed key is refused for both. LoadCarrierConfig no longer generates one. The owner still verifies frontend signatures with frontend-sign.pub. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Keep the owner address out of the add-on identity file The owner address is runtime configuration, so storing it and comparing the whole file made a moved owner refuse its own root. The identity file now holds the owner ID and storage ID only. An older file that still has an address loads, and the address is ignored. A different owner ID or storage ID is still refused. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(addons): state that an existing root loads under the owner role The owner identity no longer stores its address, so a root written by a single node loads under the owner role when the owner and storage identity match. Say so, and keep the caveat about absolute paths in the journal. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(addons): refuse library-source routes on a frontend A frontend must keep no owner state, but the library-source routes, the ApplyLibraries call and the startup official-libraries step still opened and wrote addons/sources.json in its data path. Mark the frontend role in the add-on config, also when add-ons are off. On a frontend, LibrarySources returns the unavailable error, ApplyLibraries does nothing and the startup step skips the store. The six /api/library/sources routes answer 503 with the body that the add-on feature gate writes, and an X-LocalAI-Reason header names the cause. Reads are refused too: the carrier has no verb for them. Owner and combined roles are unchanged. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(addons): put the reason in the unavailable body WriteUnavailable wrote the plain text "addon request failed", and the library-source refusal put its reason in an X-LocalAI-Reason header. Write the LocalAI error envelope instead, with a message, a type and the code "unavailable", and keep the 503 status. The message names the cause: add-ons are off on this instance, the add-on owner is not reachable, or library sources are managed on the owner. Remove the header. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): serve library calls on the add-on owner Add the carrier verbs a frontend needs to work on the library through the owner: library-list, library-add, library-update, library-enable, library-disable, library-remove, library-backend-resolve and library-backend-releases. A call carries the operation in one LibraryCall field of the wire request, so an old owner rejects it as an invalid binding. Every verb but the three reads is a mutation, and the reply is an envelope of data or a typed error, so a frontend gives the status the owner's own routes give. The owner serves them through gateway.LibraryAdmin, implemented in the application on the same LocalAdmin as the owner's HTTP routes. It runs the owner's administrator check before any store call. Add two peer-authenticated reads that take no actor and leave the audience reply unchanged: GET /addons/capabilities (protocol, calls and the owner's OS and architecture) and GET /addons/library/snapshot (the gallery-relevant source list and its version). Split the backend install: Installer.Resolve is the owner's half (resolve, pick the meta backend for the asker's capability, pin by digest) and returns a Plan; the node that installs runs the collision check and the gallery install itself. Move the source administration behind library.Admin and add library.ReconcileInfos for a source list read from the owner. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): forward library routes from a frontend to the owner A frontend refused the library-source routes and did not serve the backend library routes. Forward them instead, and keep the owner the only writer of the sources. The library-source routes work on library.Admin: the local store on a combined or owner process, the carrier on a frontend. The frontend checks the calling account (a legacy API key is refused with 401), and the owner checks the administrator right again before any store call. With add-ons off, a frontend answers these routes with a 503. A frontend asks the owner for its source list every 60 seconds through the peer-authenticated snapshot call and rebuilds its model and backend gallery lists, and the official-libraries switch, only when the version changed. If the owner does not answer, it keeps the last lists and marks them stale. Changing official_libraries on a frontend is refused with 409. The backend library install is split. The owner resolves the entry and pins the image; the frontend runs the gallery install on its own node, with its own size limit and strict mode. A frontend refuses library calls to an owner that does not serve them, or that runs on another OS or architecture. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(addons): document library operations on a frontend Replace the frontend limits that said a frontend refuses the library routes with what happens now: the library sources and the backend library go through the owner, the gallery lists follow the owner every 60 seconds, official_libraries is set on the owner, and the owner and the frontends must run on one OS and architecture. Add specs for the split owner: a frontend lists sources through the owner, a source added on a frontend reaches the owner and then the other frontend after a refresh, a write with the owner down answers 503 with the error envelope, official_libraries answers 409 on a frontend and a change on the owner reaches the frontend's gallery lists, the lists are kept and marked stale while the owner is down, a platform mismatch and a legacy API key are refused, and a frontend installs a backend into its own path from the owner's plan. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): check the shared models path with a probe Exports write into the models path of the owner, and frontends load models from their own path. A wrong mount fails silently: the export succeeds and the model never appears. The owner writes a probe file with a random nonce into its models path at start. A frontend fetches the nonce over the carrier and checks at start, then every 60 seconds, that the same file is visible at the same absolute path. On a mismatch it logs an error, reports model_exports false and blocks its export and import routes. The owner refuses an export or import while its own probe is missing, and keeps running if it cannot write the probe. An unreachable or older owner gives "unknown" and leaves exports on. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(api): describe the library refusal and forwarding The library-source and backend-library routes forward to the add-on owner on a frontend and answer 503 when the owner cannot serve them. Add the 503 to their swagger annotations, regenerate the swagger files, and say in /api/instructions that a frontend forwards these routes. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): let frontends run the backend update check through the owner In named-user mode a frontend has no user to act as, so the background backend update check failed there. Add one read-only system call for the release lookup. The owner accepts it only on the peer-authenticated route from a pinned frontend, only for backend-releases, and without an actor. Calls through /addons/forward cannot carry the mark, and every user-facing call still goes through the administrator check. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(mcp): expose the backend update check as a tool Add list_backend_library_updates, a read-only tool for GET /backends/library/updates. The in-process client reads the library installer, and the HTTP client calls the route. The six library source routes stay out of the catalog: the assistant has no per-call actor and no approval card for library changes. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(api): add export status routes for fine-tuning and quantization The add-on UIs could not know that model exports are blocked until a user hit the refusal of the export route. Add GET /api/fine-tuning/status and GET /api/quantization/status. Each returns {"model_exports": bool}, from the same check that drives the model_exports key of /api/features. The routes sit behind the add-ons gate, so they answer 503 when add-ons are off. They are listed in the swagger spec, the instructions registry, the route-feature registry and the feature docs. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): disable exports when the models probe fails The fine-tuning and quantization pages now read the new status route and turn off the export form, the checkpoint export button and the import button when model_exports is false. A short reason shows next to the control. A failed or slow answer leaves the controls on, as the server does for an unknown check. Assisted-by: Claude:claude-sonnet-5-5 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> |
||
|
Plamen K. Kosseff
|
7b9ef6a0f8 |
feat(backends): --disable-backend-install disables backend downloads. (#12754)
feat(backends): --disable-backend-install refuses every backend acquisition A hardening switch for deployments that must run exactly the backend set they were tested with (production, air-gapped, immutable images, package-managed hosts). With LOCALAI_DISABLE_BACKEND_INSTALL=1 every install and upgrade path refuses — gallery, OCI/URL/path, node-scoped, auto-upgrade, boot-time external backends — HTTP routes answer 403 up front, and a model whose backend is missing is refused before any download: 409 on the API, an error on preload and import. Whether a backend is present is asked of the execution target: the local backend directory on a single node, the workers' listings on a distributed frontend, which installs nothing itself. Backends already present, including system-path ones, keep working. Assisted-by: Claude Code:claude-fable-5 Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com> |
||
|
Stefan Walcz
|
b56b903c92 |
feat(config): let model aliases carry an opt-in profile block (system prompt, MCP, client tools) (#12661)
* feat(config): let model aliases carry an opt-in profile block An alias can now act as a profile of its target through an explicit `profile:` block carrying system_prompt, mcp (remote/stdio servers, plus the new mcp.auto) and the new client_tools. ResolveAlias applies only that block on top of a copy of the target, while Name, Model, Backend and the persisted revision stay the target's. The loader key is therefore unchanged and every profile runs on the target's backend process; today a persona needs a separate model config, which loads the weights a second time. The block is opt-in so existing aliases never change: top-level fields on an alias stay ignored, and an alias without a profile block resolves to exactly the target. A profile block on a non-alias config is rejected. A profile with its own MCP servers caches its sessions under the alias name (MCPSessionKey), because the cache slot keyed on the target's name is invalidated whenever its config hash changes and two server sets would tear each other's sessions down. mcp.auto enables all configured servers on /v1/chat/completions when the request does not name any in metadata.mcp_servers, which plain OpenAI clients cannot send. client_tools: drop discards client tools and tool_choice before the request is merged (chat completions, responses, Anthropic messages), so only the model's own MCP tools are offered. Both keys work on any model and inside an alias's profile block. Refs #12548 Assisted-by: Claude Code:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> * fix(openai): only auto-enable model MCP when MCP is enabled and permitted mcp.auto turns a plain /v1/chat/completions request into a server-side MCP request. It now applies the same controls as the dedicated MCP routes before any server is selected: the instance switch (LOCALAI_DISABLE_MCP) and, with auth on, the caller's "mcp" feature, checked with auth.HasFeatureAccess against the auth database that the chat route now passes to ChatEndpoint. A denied request is answered as a plain chat, without contacting a server or adding tools, rather than rejected: the client did not ask for MCP, it only reached a model that offers it. Endpoint specs drive ChatEndpoint against a counting MCP fixture server: MCP disabled and a user with chat but without mcp see no tools and no connection; MCP enabled and a user with mcp get the fixture tool. The user specs need the auth build tag (SQLite auth database). Assisted-by: Claude Code:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> * fix(mcp): resolve profile aliases in the MCP discovery endpoints GET /v1/mcp/servers/:model, /v1/mcp/prompts/:model and /v1/mcp/resources/:model looked the model up with GetModelConfig, which returns the alias stub. A profile alias carries its servers in its profile block, so the stub has none of its own and the endpoints reported an empty list for an alias whose chat requests do use tools. Resolve the alias the way the request middleware does before reading the MCP config, and open the sessions under MCPSessionKey so discovery shares the profile's session cache slot instead of tearing down the target's. Assisted-by: Claude Code:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> * feat(config): opt-in evidence check for profile aliases A profile with server-side MCP tools (profile.mcp, mcp.auto) runs its tools on the server and returns only the answer text. On the next turn the client sends the history back without those tool calls and results, and the model then tends to skip the tool and answer from nothing. In a measurement on a follow-up question, 0 of 12 turns called the tool and the answers carried invented numbers (e.g. "0" where the true value was 9); with the tool trail kept in the history the tool was called 12 of 12 times. A prompt instruction does not reliably prevent this, so the check sits at the output. New profile keys: profile: evidence_check: numbers: true # enables the check note: "..." # optional, defaults to an English note Rule, per request and stateless: when the check is on, no MCP tool call succeeded on the server during this request (a call that returned an error delivers no evidence and does not count), and the final answer contains a number (\b\d+([.,]\d+)?\b) that occurs in none of the request's input (the profile's system prompt and every message as received, before compression), the note is appended after a blank line. "3,5" and "3.5" count as the same number. In a streamed response the note is one extra content delta before the finish chunk. Choices that hand tool calls to the client are not checked. The setting is only read from a profile block, so plain models and aliases behave as before; a note without numbers: true is rejected at validation. Tests (Ginkgo): the number rule (invented number, number from the input, no numbers, comma/dot decimals, system prompt as evidence, tool ran), the overlay into the resolved config with plain alias, target and a top-level key as counter-checks, validation, and ChatEndpoint specs on a stubbed backend for both paths: note on an invented number, none for a number from the request, none for a profile without the check, none after a successful MCP tool call against an in-process MCP server, and the note again after a failed tool call (arguments that are not JSON). Assisted-by: Claude Code:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> --------- Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> |
||
|
mudler-agentandEttore Di Giacinto
|
c7ce0c602c |
fix: stop listing the models directory on request paths and cache GGUF header reads (#12683)
* fix(http): stop listing the models directory on embeddings and bearer requests Every embeddings request read the whole models directory before the body was parsed, even when the body named its model. On a network-backed models directory this cost seconds per request. Embeddings now binds the body first and looks up a default model only when the body has none, like chat. The pre-bind default lookup and the gpt-4o constant default are gone from that route. The first-available default lookup skips the directory when the filter cannot accept an unconfigured file. Every usecase filter rejects files without a config, so the scan never added results for them. Match-all, nil and name filters keep the scan. The bearer token check is now an exact test: a configured name, or one stat of that name in the models directory. The value is a literal, not a regular expression, and a name that is not a local relative path never matches a file. Assisted-by: Claude Code:claude-haiku-5-5 * perf(config): cache GGUF header reads for model defaults Model defaults re-parsed the GGUF header on every SetDefaults call, which runs per request and at startup reload. Put a bounded LRU in front of the parser, keyed by absolute path and validated by size and modification time. The cached value is a snapshot of the fields the defaults use, not the parser output. A changed size or mtime is a miss. Missing files and parse errors are not cached, so the existing fallback is unchanged. LOCALAI_DISABLE_GUESSING, the empty-path guard, the alias early return, the panic recovery and the context-size default are all kept in front of the cache. Assisted-by: Claude:claude-haiku-5-5 * test(http): cover listing-free default lookup on every usecase route Assisted-by: Claude Code:claude-haiku-5-5 * feat(config): persist the GGUF header cache per instance The header cache kept parsed GGUF results only in memory, so every restart parsed each model file again before its defaults were known. Write the cache to a per-instance file in the data path and load it at startup. A restarted frontend with a fixed instance ID starts warm. The file is versioned and records the estimator inputs (gguf-parser version, candidate contexts, auto context size, offload count). A mismatch on any of them makes the file ignored. Each entry keeps path, size and mtime, so a changed model file is a miss on load. Writes run on one background saver, debounced, through a temp file and rename. The entry bound applies to the file as well. Without a data path the cache stays in memory only. Documented as a per-instance exception in the model configuration docs. Assisted-by: Claude:claude-haiku-5-5 * docs(embeddings): document model selection and the no-model error Assisted-by: Claude Code:claude-haiku-5-5 * refactor(config): split the header cache into a generic cache The GGUF header cache mixed two things: the mechanics (bounded LRU keyed by path and identity, per-instance file, debounced atomic save, tolerant load) and the GGUF fields. Move the mechanics into headerCache[S], driven by a headerCacheSpec[S] that names the file prefix, schema, fingerprint, parser and the snapshot encode/decode pair. The GGUF cache becomes one instance of it. File names, the identity check, LRU size, debounce, atomic write and the corruption handling are unchanged. The on-disk JSON keeps the "estimator" key so existing files still load. Assisted-by: Claude Code:claude-haiku-5-5 * feat(config): share one GGUF header cache file between frontends Every frontend used to write its own header cache file, named after its instance ID, so a header read by one frontend was never reused by another. The cache now uses one file, header-cache.json, in the data path, for all frontends and for standalone mode. The instance ID no longer changes the file name. Frontends share the file in three ways. A save first merges the file's entries in, so one frontend's write does not drop another's entries. A miss reloads the file when its modification time has changed, and a hit never reads it. Writes go to a temp file that is renamed into place, so a reader never sees a partial file. Two frontends saving at the same moment can still drop each other's last entries. That costs one re-parse, never a wrong value, because every entry is checked against its model file before use. The shared file is valid only when every frontend mounts the same data volume. The distributed-mode and model-configuration docs state this mode and its volume limit. Assisted-by: Claude:claude-haiku-5-5 * feat(config): give an instance ID its own header cache file Assisted-by: Claude Code:claude-haiku-5-5 * style(config): gofmt the distributed config struct Assisted-by: Claude Code:claude-haiku-5-5 --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
db929f4a08 |
test(config): assert every usecase flag is a distinct bit
FLAG_MOTION and FLAG_UPSCALE were both declared as 1 << 26 on separate branches, and a merge combined the two const blocks without a conflict. Add a spec that checks every flag from GetAllModelConfigUsecases() is a single bit that no other flag uses, so a collision fails the tests. FLAG_MOTION itself moves to 1 << 27. Assisted-by: Claude Code:claude-sonnet-5-5 Signed-off-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
|
||
|
mudler-agentandEttore Di Giacinto
|
99d6b35cb5 |
perf(http): skip discovery for configured requests (#12628)
Exact configured requests need no loose-file enumeration. Reuse the synchronized config lookup without adding a cache. Misses retain regex discovery and raw-weight fallback with ALWAYS_INCLUDE. Keep general listing and bearer discovery unchanged. Preserve request validation, alias resolution, disabled-target checks, and model access. Record diagnostics only for work performed. Assisted-by: nib:gpt-6-astra Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
c3976a675b |
fix(chat): defer model fallback until after binding (#12621)
* fix(chat): defer model fallback until after binding Explicit chat models need neither legacy Bearer discovery nor default listing. Defer those fallbacks until binding finds no model, while keeping body validation and fresh binding inside each failover attempt. Expose the existing request-phase UUID through a response header and a nil-safe accessor. Disabled timing creates neither a header nor an ID. Document the contract and cover fallback, authentication, and retries. Assisted-by: OpenAI:undisclosed Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(http): check diagnostic router cleanup Assert that deferred router cleanup succeeds instead of ignoring its error. This fixes the errcheck failure in the chat authentication test. Assisted-by: OpenAI:undisclosed 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
|
0e0e91f95c |
feat(diagnostics): add opt-in profiling (#12610)
* feat(diagnostics): add private opt-in profiler Keep profiling on a dedicated loopback listener rather than the public API. Validate settings and bind synchronously so startup reports configuration and socket failures. Own sampling and shutdown for the run process. Cover private handlers, blocked cmdline access, sampling cleanup, and serving failures with focused Ginkgo tests. Assisted-by: nib:gpt-6-astra * feat(diagnostics): add sanitized phase timing Carry generated request and reload identities through private contexts. Keep timing disabled without allocations and emit only validated fields at Info level when enabled. Cover identity isolation, nested durations, inheritance, and sanitized logging with focused race-tested Ginkgo specs. Assisted-by: nib:gpt-6-astra * fix(diagnostics): retain request observations Reuse an existing request observation across recorders to avoid splitting correlation. Keep the original context, identity, and sink without new allocations. Preserve nil-recorder behavior and fresh reload identities. Verify the regression fails before the fix and passes with the full Diagnostics race suite afterward. Assisted-by: nib:gpt-6-astra * feat(cli): own opt-in diagnostics lifecycle Expose profiling and phase timing flags without enabling them for debug. Bind the private profiler before application initialization and propagate serving failures through the run lifecycle. Bound signal cleanup and preserve preload-only backend startup. Cover flag parsing, preload isolation, cancellation, and once-only shutdown. Document initialization and shutdown cancellation limitations. Assisted-by: nib:gpt-6-astra * feat(config): measure filter and reload phases Separate request lock waits from filtering and held work. Aggregate reload filesystem and parsing durations without logging inside the config lock. Preserve caller option execution under the lock after metadata collection. Extract only the internal diagnostics option before waiting for the lock. Keep direct callers uninstrumented unless they supply diagnostics options. Verify focused Diagnostics examples with the race detector, including option ordering, gated contention, errors, panic propagation, and parity. Assisted-by: nib:gpt-6-astra * fix(config): separate early reload observation Opaque callbacks cannot select timing before their execution point. Carry the startup recorder explicitly through loader construction. Apply late options once under the lock and honor composed last writes. Document early and late phase boundaries and observation identities. Report malformed gallery syntax as an internal parse failure without changing strict or non-strict loader returns. Assisted-by: nib:gpt-6-astra * fix(config): preserve per-model option callbacks The resolved snapshot suppresses existing callbacks during model defaults, even when diagnostics are disabled. Pass original options through the existing defaults pathway without adding diagnostics-driven replay. Test stateful options with two models in enabled and disabled modes. Preserve three calls and thread defaults of two and three. Assisted-by: nib:gpt-6-astra * feat(model): observe discovery phases Carry request diagnostics through config and loose-file discovery to separate directory enumeration from in-memory filtering and fallback. Keep existing APIs as background-context wrappers and preserve discovery policies, ordering, duplicates, errors, and filesystem operation counts. Add focused parity, privacy, phase, and disabled-allocation tests. The focused diagnostics race gate passes for model and galleryop. Assisted-by: nib:gpt-6-astra * feat(http): observe extraction phases Generate diagnostic identity before request discovery, independently of client correlation headers. End each extraction segment before inference so downstream latency does not inflate discovery measurements. Carry observations through discovery helpers and rebuilt request contexts without changing cancellation or model selection. Cover disabled parity, error outcomes, privacy, concurrent identity isolation and route contexts. Assisted-by: nib:gpt-6-astra * fix(http): retain diagnostics across failover Failover restores its entry request before retrying. Initialize the observation before that capture so direct extraction retains one ID. Keep extraction spans per attempt and end them before downstream work. Exercise two real targets without default middleware, including replay, shared identity, phase boundaries, and timing-off response parity. Assisted-by: nib:gpt-6-astra * feat(model): observe initialization and routing Mark loader entry before cache and admission checks. Measure only the ModelRouter callback, without attributing transport or worker latency. Test inherited identity and sanitized events with fake backends. Exercise the actual Echo router to keep profiles private across debug and timing options. Cover capture shutdown, forced close, and lifecycle failures. Assisted-by: nib:gpt-6-astra * docs(diagnostics): guide bounded investigations Document private profiling, sampling ownership, and phase boundaries so operators can interpret captures without assuming request attribution. Add Ginkgo drift checks for flags, defaults, phases, links, and capture warnings. These checks do not certify the operator prose. The focused documentation race test passes after four expected failures. The consolidated Diagnostics race gate passes across all eight packages. This gate does not validate the full suite, auth, or production UI. Assisted-by: nib:gpt-6-astra * refactor(cli): restore inline run lifecycle Remove diagnostic startup hooks so application startup stays readable in Run. Keep the profiler as an optional sidecar with bounded cleanup and an error watcher, without a general lifecycle runner. Replace hook simulations with real CLI startup checks and component capture tests. Document that application cleanup can exceed the private listener budget. The eight-package Diagnostics race gate passes. A cleanup mutation fails the real CLI listener-release regression as expected. Assisted-by: nib:gpt-6-astra * fix(cli): retain concurrent startup errors Cancellation must not hide a public API bind failure. Join the public serve result, cancellation cause, and HTTP shutdown errors inline. Ignore ErrServerClosed only after intentional shutdown. Exercise real startup with an occupied API port and a failed private listener. Isolate the Linux socket fixture in a subprocess and wait for cancellation acknowledgment without timing sleeps. Assisted-by: nib:gpt-6-astra * refactor(http): make request context primary Move context preparation into the request extractor. Diagnostics remain an optional addition, not the entry point for request processing. Preserve context initialization before failover captures the request. Assisted-by: nib:gpt-6-astra --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
c525ad16e8 |
fix(audio): record transcription usage and traces (#12546)
* fix(audio): record transcription usage and traces Count successful transcription requests by model, including streams. Keep token counts at zero because transcription exposes no token usage. Capture multipart API trace metadata without reading uploaded audio. Do not record failed transcription or client writes as successful usage. Assisted-by: Codex:gpt-6-astra * fix(audio): preserve aliases in streaming usage Streaming transcription records the resolved target as its usage model. Pass the requested name so JSON and SSE requests share the alias bucket. Assisted-by: Codex:gpt-6-astra * test(http): check multipart reader close errors Assert successful reader cleanup to satisfy the errcheck CI gate. Assisted-by: Codex:gpt-6 --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
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
|
9eb5a9e61d |
feat(audio): remember speakers from diarization (#12414)
* feat(schema): validate portable speaker profiles Add the versioned profile schema for explicit speaker enrollment. Validate compatibility against separately supplied loaded-encoder metadata. Reject unusable speakers, invalid vectors, and inconsistent clean spans. This slice does not change HTTP routes, backend integration, or the UI. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(parakeet): export profiles with transcripts Export opt-in speaker profiles and trusted encoder metadata. Replay registrations by ID so duplicate display names keep independent vectors. Use one profile-capable diarization for slots, names, and clean spans. Assign timestamped ASR words to those slots without a second diarization. Preserve legacy opt-out and no-ASR behavior, and propagate failures. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(audio): enroll portable speaker profiles Gate profile exports with voice-recognition permission and validate registration against metadata from the loaded encoder. Preserve audio enrollment and independent registrations with duplicate display names. Exclude diarization and registration exchanges before API trace capture so persisted traces cannot retain profile vectors or JSON audio. Defer candidate dimensions to trusted loaded metadata. Sort candidates by registration ID so incompatible profiles cannot suppress legacy voices through registry iteration order. Keep portable identity checks closed when trusted metadata is unavailable. Test persisted traces, explicit slot zero, and selection through offline and live transport. Document privacy and the ephemeral registry lifecycle. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): remember speakers from diarization Add a Studio page for diarization and opt-in speaker profiles. Preview clean intervals from the original recording before explicit registration. Join profiles by raw speaker labels, preserve duplicate names, and relabel turns only after a successful save. Discard stale results when the model or recording changes. Share registration metadata with voice management without storing vectors or recordings from this flow. Document permissions and the global, ephemeral registry. Cover enrollment, permissions, previews, and asynchronous races with mocked Playwright tests. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: clarify HTTP speaker enrollment support Replace the stale enrollment limitation with the current HTTP workflow. Distinguish native transport from explicit registration and link its docs. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(parakeet): pin merged speaker profile support Use the merged commit from mudler/parakeet.cpp#80. Its tree matches the previously accepted native pin. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: add diarization enrollment setup example Connect the existing gallery modes to the speaker enrollment workflow. Show installation, private profile export, explicit raw-slot registration, and later recognition without another export. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(blog): explain diarization speaker profiles Put the diarization walkthrough on the LocalAI website in the feature PR. Cover the three gallery modes, explicit enrollment, and privacy limits. Link setup instructions and keep availability conditional on feature support. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(blog): focus diarization on everyday use Explain what users can do with recordings before the setup steps. Replace the technical walkthrough with a short Studio guide and link readers to the existing reference for model names and developer use. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(blog): lead with speaker capabilities Present speaker recognition through everyday uses and a short UI flow. Keep technical reference details in the existing documentation. Assisted-by: OpenAI:unknown Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(diarization): satisfy Go lint checks Avoid copying protobuf message state when extending backend status, check the multipart reader close result, and document the focused testing.T lint exemptions. 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> |
||
|
Ettore Di Giacinto
|
d8571a8ee9 |
fix(failover): spill 429 admission rejections to the next target
#12113 changed admission control to reject with 429 instead of 503. failoverWriter only held back responses with status >= 500, so a 429 rejection reached the client and the chain never spilled to its next target. Hold 429 as well. An admission rejection is still flagged and spills without tripping the target. Any other 429 is not retryable, so it is released to the client unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-5-5 [Claude Code] |
||
|
Ettore Di Giacinto
|
9c156656bd |
Merge PR #12285: feat(failover): serve a model name from a chain of local and remote targets
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Stefan Walcz
|
950c271710 |
[router] fix: re-seed the knn corpus index when the vector store comes back empty (#12267)
fix(router): re-seed the knn corpus index when the vector store comes back empty The corpus manager records a store as synced by file fingerprint and embedding fingerprint. The local-store backend behind it is an in-memory gRPC process the model loader may evict (active-backend cap, memory pressure) or the idle watchdog may kill, and relaunch on the next request — empty. The file is unchanged, so EnsureLoaded returned early and the router went blind: every probe fell back with similarity 0 while corpus/stats kept reporting the full count. Measured on a production router (LOCALAI_MAX_ACTIVE_BACKENDS=6, four resident models + two router stores): loading any further backend evicted a store, and the idle watchdog killed both after 15 minutes; /stores/find returned 0 hits against a 100-line corpus file whose stored vectors matched fresh embeddings with cosine 1.000. Two parts, because the knn classifier is built once and cached (GetOrBuildClassifier), so the sync at build time is otherwise the only one for the process lifetime: - corpus.Manager remembers one vector it inserted (probe) and, on the synced path, asks the live index for it. A miss means the index was relaunched — fall through and re-seed from the file (no re-embedding). - The router middleware wraps the knn classifier's store so every lookup runs EnsureLoaded first; the loader gets the raw store, so its probe never re-enters the wrapper. A sync error fails the lookup closed, like the build-time load. Specs: corpus package (relaunched empty store is re-seeded under an unchanged file), middleware (relaunched index behind the cached classifier is re-seeded instead of falling back; the spec is red without the wrapper). The test fake now answers Search for inserted vectors. Folds in the maintainer's follow-up (router-corpus-reseed-after-store-relaunch): reviewed and accepted. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de> |
||
|
|
52a6d62bbc |
fix: return correct HTTP status codes for saturation and no-nodes-available (#12113)
* feat: return 429 when backends are saturated When backends are at capacity (per-model max_concurrent or the process-wide --max-concurrent-backend-requests ceiling), the response was 503. The OpenAI SDK, litellm, and most agent harnesses key on 429 for rate-limit backoff and treat 503 as a hard error. Both saturation paths now return 429 with the existing Retry-After header and type: "rate_limit_error" in the JSON body. The per-model admission middleware keeps admission_rejected as the code field so existing alerts that match on it still fire. Non-saturation 503s are unchanged: model cold-loading (with progress body), model-load failure cooldown, PII detector fail-closed, and classifier unavailable. These mean "not ready" rather than "busy". Assisted-by: AGENT:regolo/glm5.2 [TOOL] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: return 503 when scheduler has no available nodes When the scheduler cannot find any healthy node to serve a model — all nodes are full and eviction cannot free a slot, or a node_selector excludes every candidate — the error fell through to 500. A 500 tells clients something is broken when the condition is transient and retryable. The router now wraps these errors with a new ErrNoAvailableNodes sentinel. The HTTP error handler maps it to 503 via applyNoAvailableNodes, following the same pattern as applyBackendAdmission (429). Unrelated scheduler errors (DB timeouts, registry lookups) still return 500. Three return sites are wrapped: - resolveSelectorCandidates: selector matches zero healthy nodes - scheduleNewModel eviction-busy: all models have in-flight requests - scheduleNewModel eviction-failed: eviction itself errored The existing scheduleAndLoad wrapper ("no available nodes: %w") preserves the sentinel through the chain via errors.Is, as does ModelRouterAdapter. Assisted-by: AGENT:regolo/glm5.2 [TOOL] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(http): use Ginkgo for admission tests Replace forbidden testing.T calls with Ginkgo and Gomega so the lint check accepts the admission handler tests. Assisted-by: Codex:GPT-6 forbidigo * fix(middleware): show the recorded status for admission rejections The admission audit row now records 429, but the Middleware page still printed a hard-coded 503. Read the status from the event, and update the two package comments that still said 503. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 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> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
00bd5ee121 |
fix(failover): skip a target that has been edited into a chain
A chain is checked for nested chains when it is saved, but not when one of its targets is later edited into a chain. Requests then served the inner chain's config as the target, which has no backend and triggers backend auto-detection. Mark such a target missing so no plan picks it, and skip it without a trip in the HTTP path when it is pinned. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-5-5 [Claude Code] |
||
|
Ettore Di Giacinto
|
5ed67be0bf |
fix(failover): skip a target that answers HTTP 501 instead of failing the chain
The non-OpenAI endpoints (depth, detection, face_*, voice_*, images, video, 3d) map a backend's gRPC Unimplemented to an echo 501 without the gRPC status. The retry loop did not see a capability gap, and IsRetryable is false for 501, so the client got 501 and the next target was never tried. Treat a returned or written 501 as a capability gap. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
882f51fd62 |
fix(failover): trip a rate-limited or exhausted target instead of skipping it
Treating ResourceExhausted as a capability gap skipped the target without counting a failure, so a target that stays rate limited or out of memory kept its traffic. It is now an ordinary retryable failure: the request moves to the next target and the exhausted one trips. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
6df1767133 |
fix(localai-proxy): keep rerank, stream errors and chat intact through the proxy
Rerank no longer sends top_n 0, which the upstream rejects. A mid-stream upstream error frame now fails the call instead of ending it as a short success. Temperature 0 is forwarded. An upstream 429 becomes ResourceExhausted, which failover skips like Unimplemented. A localai-proxy config sends its own name upstream when upstream_model is unset, and a chat proxy defaults to the tokenizer template so chat reaches the upstream as messages. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
509cca35e0 |
feat(grpc): serve Rerank from Go backends and skip Unimplemented targets
Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
2ecbaab010 |
fix(failover): send remote targets their own upstream model
A chain request reached a cloud-proxy target with the client's model, the chain name, whenever the target set no upstream_model: passthrough forwards the body's model and translate falls back to it. The upstream answered 404, which neither retries nor trips, while the liveness probe, which checks the target's own name, kept passing. PrepareTarget now sets the upstream model of a remote target to proxy.upstream_model or the target name, the same name the probe uses. The request pipeline and realtime chain stages both call it. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
b67b75dcdd |
fix(failover): answer HasChains from a flag set at sync
The request path called HasChains on every request, and with no chains it scanned the config source each time: the loader's lock plus a copy and sort of every config, forever, on every installation without chains. Sync now keeps an atomic flag and HasChains reads only that. A chain added since the last sync is still served because Plan syncs on a miss; only in-request retry waits for the next tick (at most 1s). Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
f28d07b09d |
fix(failover): spill capacity and disabled targets without tripping them
An admission rejection or a disabled target moves the request to the next target through Attempt.Skip, which records no failure. A 4xx response no longer counts as a success. Requests skip body recording when no chain is configured, and stop it once the model is known not to be a chain. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
471bd8bf96 |
feat(failover): resolve chains per request and retry on the next target
The retry wraps SetModelAndConfig, so each attempt binds the request again from a replayed body. A 5xx of a chain request is held back until the handler returns, and a streamed response is never retried. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
636c43baa5 |
fix(openai): return HTTP errors for pre-stream failures and report per-slot context (#12204)
* fix(capabilities): report the per-request context with split KV slots With parallel slots and kv_unified:false, llama.cpp gives each slot n_ctx/n_parallel, padded up to a multiple of 256. /models/capabilities still reported the full n_ctx. A client that budgets a request against context_size then overflows at a fraction of it. EffectiveRequestContextSize returns the per-slot size in that case and the full context otherwise. With the unified KV cache, the grpc-server default, one request may use all of n_ctx. The capabilities endpoint and the router's prompt trimmer now use it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(openai): return an HTTP error when a stream fails before any chunk A streamed chat request set the SSE headers, then waited for the backend. When the backend failed before the first token, LocalAI sent a 200 with a `data: {"error":...}` chunk and [DONE]. Clients that do not parse error chunks saw an empty reply. cogito's LocalAI client was one of them: nib users got "streaming decision produced no content" instead of the context overflow that caused it. Nothing has been written at that point, so the handler now returns the error as a normal HTTP response. A failure after the first chunk keeps the in-stream error chunk. A prompt that exceeds the context is now a 400 on both paths, as in the OpenAI API and llama-server, and no longer a 500. The message is kept whole, because clients read the token counts from it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(e2e): check the error from closing the response body golangci-lint's errcheck flags the unchecked resp.Body.Close in the new pre-stream error helper. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> 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> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Richard Palethorpe
|
7034d353b1 |
feat(kimodo): Add observability hooks (#12184)
feat(kimodocpp): add API and backend request observability Capture animation requests, phase timings, output metadata, and failures in traces. Record correct API error statuses and cover completed, running, failed, and disabled tracing. Assisted-by: Codex:GPT-6 Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
Richard Palethorpe
|
495165266f |
feat(kimodocpp): track usage through generic backend metadata (#12162)
Report input tokens and frame-step output units in response metadata and record them through the existing usage accounting pipeline. Preserve the accounting rule and model-specific dimensions as JSON without extending the gRPC schema for each modality. Expose animation usage only under metadata.usage, validate counts before recording, and document the response contract and loaded-model location. Add coverage for transport, defaults, failures, persistence, and recording requests once with statistics enabled or disabled. Assisted-by: Codex:GPT-6 Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
lei_lei
|
f28e8b24e6 |
fix(ollama): accept :latest tag on model lookup (#11732)
/api/tags appends :latest to untagged names, but chat and the other model endpoints looked the tagged name up as-is and 404'd. Signed-off-by: lei_lei <96427312+leilei3167@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
df1a40f9c0 |
fix(distributed): hash the config as persisted, not as defaulted
The revision was computed after SetDefaults, which folds in things that are not persisted configuration: the GGUF guess, the hardware defaults, and app-level options such as threads. The GGUF guess is the damaging one. It parses the model file to fill in values like context size, and when that parse fails it falls back to a different default. Whether a multi-gigabyte file on network storage parses at a given moment is not a property of the configuration, so one unchanged YAML produced two different revisions depending on when it was read. The controller rejected every request carrying the other one, and the model stayed unroutable until the stored value happened to match again. This is why it never reproduced against a model directory with no weights in it: the guess is skipped there and both values agree. The app-level defaults are the same class of bug with a slower fuse: changing threads in the settings UI changed every model's revision and made every model unroutable. The revision is now stamped when the file is parsed, before any defaults are applied, so it is a function of the file alone. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [golangci-lint] |
||
|
Ettore Di Giacinto
|
f3fabe8c5c |
fix(distributed): order derived usecases deterministically
syncKnownUsecasesFromString rebuilds KnownUsecaseStrings by ranging GetAllModelConfigUsecases, which is a map. Go randomizes that order per call, and the field is part of the serialized config, so one unchanged YAML hashed to a different config revision on every load. A model that derives a single usecase hid the problem. One that derives several, such as a chat model with an mmproj, alternated between as many revisions as there are orderings. The router treats a revision it did not establish as a config change, so requests failed with "stale model config revision" until the stored value happened to match again. Sorting the list makes the revision a function of the file alone. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [golangci-lint] |
||
|
Ettore Di Giacinto
|
04735cd1f6 |
fix(distributed): stamp config revision at load time
The request middleware merges the caller's prediction parameters into its copy of the model config. core/backend.ModelOptions then hashed that copy, so the revision identified the request body rather than the persisted configuration. EstablishModelConfigRevision stores the first revision it sees and requires an exact match afterwards. The first request after a restart therefore pinned the model to its own temperature, top_p and stop values, and every later request that sent different ones failed with "stale model config revision". No config edit was involved. The loader now stamps the revision when it materializes a config, before any request override reaches it, and ModelOptions reads that stamp. Model administration keeps hashing the same persisted config, so both paths agree on one revision per configuration. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [golangci-lint] |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
0761bd02c7 |
feat(chat): add end-to-end context compression (#11556)
* feat(config): add context compression policy Define the opt-in model configuration contract before the chat middleware consumes it. Document each policy field so later request handling does not invent a second schema.\n\nRefs #9534\n\nAssisted-by: Codex:gpt-5 * fix(config): register compression fields The model editor metadata gate rejects new config fields without descriptions and suitable controls. Register the compression policy so operators can edit its six fields safely. Assisted-by: Codex:gpt-5 [monitoring-prs] * feat(chat): compress long contexts Long conversations currently fail once they reach the model context window. The opt-in policy now summarizes complete older turns before primary inference and preserves the newest tool chains. Both OpenAI and MCP chat routes share the same transformation. Usage metadata and metrics expose each compression event. Refs #9534 Assisted-by: Codex:gpt-5 --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
Richard Palethorpe
|
d10374f849 |
feat(router): make KNN a first-class classifier with a persisted, curated corpus (#10652)
* feat(router): make KNN a first-class classifier with a persisted, curated corpus
Add `classifier: knn` — similarity-weighted voting over labelled
example prompts. Unlike score/colbert it needs no classifier model:
label knowledge lives in a corpus seeded and curated through the
admin API, so routing decisions are deterministic, auditable, and
grounded in graded experience rather than a model's opinion.
Epistemic gate: corpus entries below knn.similarity_threshold cannot
vote; when none clears it the classifier activates no labels and the
router uses the fallback — a prompt unlike all labelled experience is
treated as undecidable, not guessed. Decisions record
nearest_similarity (also on fallback rows) so admins can see how far
the nearest labelled experience was; the Routing tab explains
out-of-corpus fallbacks and shows per-label corpus counts.
Persistence: one JSONL file per router under
<data path>/router-corpus (text, labels, vector, embedder
fingerprint). The file is the source of truth; the local-store index
is rebuilt from it at classifier build time and stays a pure
in-memory index. Entries recorded under a different embedding model
re-embed on load. Also corrects the docs' false claim that
local-store collections persist — the embedding cache never survived
restarts (and still doesn't); the corpus does.
Corpus input is API-only by design (entries may contain example user
content): POST /api/router/{name}/corpus seeds (labels validated
against declared policies, embedded server-side, indexed
immediately), GET .../corpus/stats inspects — label counts only,
entry texts are never returned by any surface — DELETE .../corpus
wipes. Admin-gated like the sibling router endpoints, and exposed as
MCP tools (seed_router_corpus / get_router_corpus_stats /
clear_router_corpus) in both the httpapi and inproc clients with
coverage-test route mappings.
Plumbing: VectorStore gains SearchK (top-K was hardcoded to 1);
local-store gets InsertBatch/Delete as optional fast paths;
RouterConfig gains a knn block (embedding_model, k,
similarity_threshold, vote_threshold, store_name) with meta-registry
fields; the classifier dropdown now offers knn and the
previously-missing colbert; embedding_cache is ignored (with a
warning) for knn — it IS an embedding-KNN lookup; the stale
/api/instructions intelligent-routing entry is rewritten (it
described a classifier that no longer exists); swagger regenerated.
Tests: KNN vote/gate specs with hand-computed vote shares, corpus
manager suite (restart reload without re-embedding, fingerprint
re-embed, dedupe, hostile store names), middleware specs (corpus
routing, gate fallback, config validation, cache-wrap refusal),
corpus endpoint specs pinning the texts-never-returned contract, MCP
catalog + route-mapping gates, and a Playwright spec for corpus
stats and the out-of-corpus decision detail.
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(router): name consulted corpus neighbours in knn decisions
Every knn decision (decision log rows and the /api/router/decide
response) now carries neighbors: the K retrieved corpus entries by
descending similarity - including ones below the epistemic gate, which
is what makes fallback decisions diagnosable - each as {id, similarity,
labels}. The id is the entry's content hash (first 8 bytes of the
SHA-256 of its text, hex): stable across reseeds and re-embeds, and
text-free, so an external platform that seeded the corpus can recompute
text->id on its own copy and bucket decisions by corpus region (per-
region reliability accounting) without corpus text ever leaving the
server. A corrupt index payload surfaces as an id-less neighbour at a
real similarity instead of disappearing.
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* refactor(router): deduplicate knn plumbing and cut corpus hot-path waste
Post-review cleanup of the knn-first-class-router branch; no behaviour
changes on the API surface.
Reuse/altitude:
- RouterKNNConfig.ResolvedStoreName is now the single source of the
router-corpus-<name> default (was hand-derived in four files).
- corpus.ResolveKNNRouter + corpus.Seed carry the shared model
resolution and seed validation; the REST endpoints and the assistant
MCP client are thin transport adapters over them, with sentinel
errors mapped to HTTP statuses at the echo boundary.
- middleware.NewClassifierDeps assembles the classifier dependency set
once for all five entry points (OpenAI, Anthropic, realtime, decide,
corpus) instead of five hand-copied literals.
- router.AllClassifiers feeds both the status endpoint and the
unknown-classifier error, ending the classifier-list drift.
- Per-classifier requirements moved out of validateRouterPolicies into
their buildClassifier arms; the knn arm owns its embedding_cache
opt-out instead of a name-check in the shared wrap tail.
- adminOnly replaces four inline copies of the admin gate in the
middleware routes.
- localVectorStore.Search delegates to SearchK (identical traces).
Efficiency:
- Manager.Add embeds outside the manager mutex and appends to the
JSONL file (O(new) instead of O(corpus) rewrite); a torn tail from a
crash mid-append is tolerated on read and repaired on next write.
- Stats memoises per store keyed on the file's stat fingerprint and no
longer takes the manager mutex, so the 5s status poll stops parsing
vector-laden JSONL and stops blocking behind seeds.
- KNN Classify decodes each neighbour payload once (was twice) and
builds refs and votes in a single pass with one fallback return.
- Corpus file writes fsync before rename/close.
- The corpus manager is built eagerly in newApplication (sync.Once
dropped); test helper dead branch removed.
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(router): bind knn corpus vectors to an embedder fingerprint and fail closed on mismatch
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(mcp): align corpus tool prompts and the mutating-tool safety list
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(proto,backend): report embedding shape from the llama-cpp backend
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(embeddings): Go-side pooling — mean/last/decayed_mean with half-life
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(embeddings): accept chat messages[] and per-request pooling on /v1/embeddings
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(middleware): name the failing fields when post-merge validation 400s
An intermittent post-merge validation failure surfaced as an opaque 400
during integration (pooling scheme mismatch that no client had sent).
Log the model, the request's pooling override, and the merged config's
pooling fields at the failure point so the next occurrence identifies
whether the request or the stored config carried the bad value.
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(embeddings): scheme override must not inherit the config's half-life
A model config defaulting to decayed_mean pooling carries
pooling_half_life_tokens; a request overriding the scheme to mean/last
without its own half-life inherited that value, and post-merge
validation rejected the pair the server itself had assembled. Zero the
inherited half-life when the overridden scheme is not decayed_mean; a
request that explicitly pairs a half-life with a non-decayed scheme
still 400s.
Assisted-by: Claude:claude-fable-5 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix embedding pooling validation and router bounds
Declare backend embedding layouts and reject incompatible pooling modes. Reset local-store dimensions after a full clear, validate KNN thresholds, and add real backend and store integration coverage.
Assisted-by: Codex:gpt-5
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* ci: run local-store integration tests
Build and install the local-store backend in the Linux test job, then run the existing store integration suite so new specs are discovered automatically.
Assisted-by: Codex:gpt-5
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
|
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
9f62401fca |
feat(traces): show in-flight API requests (#11368)
Register JSON API exchanges before their handlers run so the traces dashboard can surface active work. Replace the live entry with the completed persisted record under the same ID, and clean it up if a handler panics. 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
|
58ea2f5d79 |
feat(ui): give Operate and Studio a front door, and fix two layout regressions (#11305)
* feat(ui): give Operate a front door and fold six rail groups into four Opening Operate ran firstVisiblePath() and landed on Backends, because Backends happens to be written first in operateConsole.groups. The section that should answer "is anything wrong" opened on a package manager, and nothing was reported until you visited it. Adds /app/operate. Its one irreplaceable block is "Needs attention", which is empty when nothing is wrong and says so in a line rather than rendering a reassuring green panel. It collects stale backends, failed operations and unhealthy nodes. Everything else on the page is a summary you could already assemble by visiting four others. The rail regroups from six headings to four: Inference and Activity were both "the runtime right now", Access and System were both administration. No destination is removed and no gate changes, so isConsoleItemVisible and consolePaths are untouched. Overview leads the first group, which is what makes firstVisiblePath() return it without knowing it exists. Rail entries now carry a signal beside the label. This does not replace the sidebar badge and is not built as if it does: the badge stays on the always-visible sidebar entry for the reason recorded in Sidebar.jsx, that the rail exists only on Operate routes and can be collapsed. The signals are orientation while inside Operate, so they are aria-hidden and nothing urgent depends on them alone. OperateSummaryContext polls once for the whole console, following OperationsContext, which exists because per-consumer setInterval against one endpoint was the defect it fixed. It is mounted by ConsoleLayout for the Operate console only, so "poll only while in Operate" needs no route check. Built on usePolling, so it pauses on a hidden tab. Operations are read from OperationsContext rather than polled a second time, and each source degrades to no-signal on its own so one dead endpoint cannot blank the rest. It reads the cached GET /api/backends/upgrades and never the POST that forces a real registry check. Traces and Usage get no signal yet: /api/traces returns the list, so a count would mean fetching every trace to render one number. A counts endpoint is the honest fix and is scoped separately. Full e2e suite green (369 passed, 4 skipped), including a render-smoke entry for the new route. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): open Studio on what this machine can actually make Studio was a tab strip over six generators that opened on Images, which was never a decision, only the first entry in BASE_TABS. Nothing said which modalities this installation could run, so the way to learn that video had no model was to pick the tab and find an empty select. Adds an overview tab and makes it the fallback. Explicit tabs still win, so existing deep links keep working; anything unrecognised or gated now lands on the overview rather than Images. Each tab carries a dot: filled when an installed model advertises that modality, hollow when nothing serves it. That is the feature in one detail, turning the strip from navigation into a report of what the machine can do before anything is clicked. The dot is aria-hidden because the overview states the same facts in words and the dots change as models load. Two kinds of unavailable, which had to stop looking alike: - switched off, via a permission: no tab and no lane, unchanged - available with no model: a lane, and a route to installing one Studio now owns one MODALITIES table so the tab strip and the overview cannot disagree about what exists, and calls useModels() once, unfiltered, grouping in the browser. useModels(capability) fetches the whole list and filters locally, so a hook per modality would have been six identical requests to /api/models/capabilities on every mount. There is a test for that. Recent outputs read every localStorage store through a new readAllMediaHistory(), which avoids mounting five hooks that carry save timers the overview has no use for. 3D is read separately through use3DHistory rather than folded in: its entries are GLB blobs in IndexedDB, so they cannot come from the same synchronous read. Typical cost is the median of this machine's own history, not a guess, and renders as a dash when there is nothing to go on. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * fix(ui): stop the stat cards and the console rail breaking on small screens Two unrelated causes behind one report that /app/manage looks wrong when the window is narrow. The stat cards were being laid out by the wrong rule at every width. Two different components both claimed `.stat-grid`: the dashboard card strip that holds .stat-card children, and the detail-pane StatGrid the split views introduced further down App.css. Being later, the second won every shared property, so the cards got its 120px columns and its 1px hairline gap in place of their own 180px columns and spacing-md. Four cards were packed onto a row that fits two, labels wrapped to three lines and clipped, and the icon crowded the value. Renamed the strip to `.stat-cards`, after the children it actually holds, which also removes the mismatch of a `.stat-grid` container full of `.stat-card`s. The split-view component keeps `.stat-grid` and its BEM parts. The expanded console rail had no bounded height. Thirteen destinations stacked in one column is taller than a phone, so opening the menu pushed the page's own heading past the fold: the menu replaced the page rather than annotating it. Capped at 55vh with internal scrolling below 768px, so the content behind stays reachable. Both are asserted on behaviour rather than markup: no stat-card label may be clipped, the card gap must not be the detail pane's hairline, and expanding the rail must leave the page heading on screen. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): retemper the palette to localai.io and add the lane primitive The token half of the style transfer, plus the shared list idiom the two overviews had each grown their own copy of. theme.css moves from Nord to the website's palette, variable names preserved so every consumer moves with it: ground #13171f -> #0d1117, accent frost cyan #88c0d0 -> action blue #4f8cff, success sage -> mint #56d6a4, warning -> the amber #f1b95d the site spends only on the thing asking for a decision. Eyebrows go mint. Dividers become an opaque #29384a hairline rather than alpha over a varying surface, which is what makes stacked surfaces read crisply on the site. Light is derived, not inverted. The site ships one theme and never had to answer this, but the app does: blue darkens to #2f62d8, mint to #0d8b60 and amber to #8a5d0b, all clearing 4.5:1 on a cool paper ground, where the dark-mode values sit near 2:1. Same three roles, different values. Three files restate the palette because CSS variables cannot reach them: cmTheme.js (the whole CodeMirror theme), VoiceVisualizer and WaveformPlayer (canvas). Left alone they would have quietly kept the app half-Nord. The `.lane` primitive replaces the near-identical row CSS that OperateOverview and StudioOverview had each written: a full-bleed row on a hairline that insets on hover, with no card and no shadow. Callers supply only the column template. Both pages now use it, along with `.lane-head` for section rhythm and a `.page-pad` container for top-level pages outside a console shell — without which Studio sat flush against the sidebar with its eyebrow clipped. Studio's tab strip wraps rather than running off the edge at narrow widths. Full e2e suite: 386 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): put Home's resident models on lanes and give the footer one line Home's status line was three chips saying a thing was true. It now reports figures: how many models are resident, how many nodes are healthy, what share of memory is in use, set in tabular monospace so the digits line up. A chip answers whether; a figure answers how much, which is what someone opening the page at a glance is after. Resident models move from status chips to lanes, with the id set in a new `.lane__name--id` because an id is something you might type or paste and the UI face makes it read as a label. /api/system-information carries only the id, so there is deliberately no backend or memory column: inventing one would mean a server change this does not make. The footer was three centred rows and cost the bottom sixth of every page for chrome. It is one line now, version left and links right, wrapping to centred when the viewport is too narrow to hold both. Every link it had, it keeps. Full e2e suite: 392 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * fix(ui): correct three contrast failures and stop a guaranteed-404 poll A contrast audit of the new palette found three values below WCAG AA, one of which the previous commit message claimed was fine: - White on the #4f8cff button is 3.22:1, which is large-text only. The website does exactly this, but a button label in an app is not large text, so the label goes to dark ink at 5.88:1. Light mode keeps white, which is 5.44:1 on its darker blue. - Light-mode success was 4.08:1 on paper, not the 4.5 claimed. Darkened to #0a734f, 5.56:1. - Nord red was already 4.28:1 on raised surfaces, a pre-existing miss carried over unexamined. Lifted to #c96f78, 5.02:1. Lanes gain the two states they were missing: a 44px target on coarse pointers, matching what EntityRail already does so the two list idioms feel the same under a thumb, and a reduced-motion variant that keeps the background feedback while dropping the hover inset, which is a position change. The Operate summary no longer asks for /api/nodes on a single-node install. The cluster API answers 503 when distributed mode is off, so it was a guaranteed miss every fifteen seconds; it is now gated on useDistributedMode, the same condition the rail already uses for the Nodes entry. Full e2e suite: 392 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * fix(ui): restore the gap between overview blocks, and stop claiming zero nodes Two defects a design review surfaced. `.lane-head:first-child { margin-top: 0 }` was meant to stop the first block on a page carrying a top margin. But every <section> makes its lane-head a first child, so the reset applied to all of them and the gap between blocks vanished: "Sections" sat flush against the attention row above it. The header supplies its own bottom margin, so a uniform top margin is correct everywhere. The Cluster summary read "0 nodes" on a single-node install, which looks like a fault when the cluster API is simply switched off. It now says "Single node". Full e2e suite: 392 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): open dark by default, and stop clipping the collapsed sidebar footer Dark is the identity rather than a preference: localai.io ships one theme and it is this one, so an install should look like LocalAI before anyone has chosen anything. The OS setting no longer selects light on first load. The toggle still does, and a stored choice wins forever after, which the tests assert both ways. The collapsed sidebar footer stacked its controls but kept the expanded row's inline padding, so their edges were clipped against the 51px rail. Full e2e suite: 394 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(api): count traces server-side and give the Operate overview real totals The overview's headline block had no source. /api/traces returns the trace list, so "37 errors in 24h" meant fetching every buffered exchange to count it in the browser — waste that grows with the buffer, to produce three integers. Adds GET /api/traces/summary: totals, failures, p95 and a bucketed series for sparklines, over a window that defaults to 24 hours and is capped at a week. Deliberate calls, each with a spec: - A 4xx is the caller getting it wrong, not the installation being unhealthy, so only 5xx and transport errors count as failures. - p95 is a nearest-rank percentile rather than the slowest request, which is what a max would report and what makes latency panels lie. - Buckets are oldest-first so a sparkline reads left to right, and the slice is never nil: nil serialises as null and breaks .map() on the other side, which is a silent runtime error rather than an empty chart. - Exchanges outside the window are not counted at all. The route is registered before /api/traces/:id so "summary" is not captured as a trace ID. On the client, Traces and Usage gain the rail signals they were shipped without, the Observability section summary now states counts instead of listing its destinations, and an installation that has served nothing says so rather than showing three zeroes dressed as telemetry. Sparkline is a bare stroke with an emphasised endpoint and no axes: the figure above it already states the value, so its only job is the shape. Go: 185 middleware specs pass. Full e2e suite: 396 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * fix(ui): stop the memory chart calling a trade-off an error The VRAM-by-context chart rendered any build over the limit in error red, and escalated the verdict to the error tone as soon as two context sizes crossed it. But an over-limit build still installs — #11288 keeps a test on exactly that — so red overstates what is happening. A model that fits at 32k and not 64k is a trade-off, not a fault. Over-limit bars and the limit line now use the warning tone, which is the constraint colour used everywhere else in this branch: know what you are doing, not you may not. The error tone is reserved for "fits nowhere", where the model genuinely cannot run on this host. Full e2e suite: 397 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): give the new surfaces orchestrated motion Uses the reveal system already in the codebase rather than adding a library: pageReveal, .reveal-stagger and staggerStyle() were built for exactly this, and anime.js would be ~17KB duplicating four lines of CSS for list reveals. The overview's headline figures, attention rows and section lanes stagger in, as do Studio's modality lanes and recent outputs, so a page assembles in the order it is read instead of appearing all at once. Two additions beyond stagger. Rail signals transition on opacity when a poll lands, so a number changing reads as an update rather than a jump cut, and it stays on the compositor so it cannot reflow the rail. The attention block animates its left edge in — the one thing on the page that should announce itself, and on the border rather than the text so nothing moves under a reader. Both are dropped entirely under prefers-reduced-motion, alongside the lane hover inset already handled. Full e2e suite: 397 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): put the generators on a hairline field stack and record the request The workbench treatment from the mocks, applied where it costs least: both changes land on shared surfaces, so all six generators get them at once rather than drifting apart page by page. The control column stops being a shadowed card of boxed groups and becomes a hairline field stack — the panel is the page's left half, not an object floating on it — with uppercase micro-labels matching the eyebrow treatment used elsewhere. Because .media-controls is shared, Images, Video, 3D, Speech, Sound and Audio FX all move together. RequestPanel shows the request the form actually built, with a copy-as-curl. LocalAI is API-first and Studio is the best place in the app to teach its own endpoints: the form stops being a black box, and a result worth keeping can be reproduced from a shell without reverse-engineering which fields the page sent. It records what was sent rather than what the form currently holds, and renders nothing until a request has been made — a panel describing a request nobody made is a tutorial, not a record. Wired into Images and Speech. Full e2e suite: 401 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): make Chat a transcript instead of a bubble thread Rounded, filled, asymmetric bubbles fight a system built on hairlines, and they carry the speaker in shape and side rather than in words. The assistant side had already given up its bubble; this finishes the job. Both roles now run full width down one column, separated by a rule, each with a mono role label. The user turn keeps a left edge in the action tone so the two are still told apart at a glance, without a fill or a corner radius. The avatars go: the accent and the label carry the speaker, so the glyph was decoration once neither side had a bubble. Saying who is speaking in words rather than in geometry is also what survives being read aloud, printed, or looked at by someone who cannot pick the sides apart by colour. Full e2e suite: 404 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * feat(ui): dress the API reference in LocalAI's palette The Swagger page was the last surface still shipping in someone else's colours, which is conspicuous now that everything it links from is dark. Swagger UI has no theming hook, so rather than fork it we serve our own index ahead of the library's wildcard and restate the palette over its stylesheet. The library's own bundle and assets are still what load, so a swagger-ui upgrade cannot silently break the page — this is a skin, not a fork. Two things needed real care. Swagger tints the entire operation row per method via .opblock.opblock-post and friends, so the palette had to match that specificity rather than reach for !important; the method now lives on one edge instead of washing across the row, because a page where every row is a status colour has no status colour left. And the filled method chip put white on pale green, which was the least readable thing on the page — it is an outlined mono chip now, carrying the method in its border and text. Palette values are copied from theme.css rather than referenced: this page is served by Go and never sees the app's CSS. The comment says so, and says to keep them in step. Go: routes and middleware suites pass. Full e2e suite: 405 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] * fix(ui): make tall split-view pages reachable, repair the Agents header, scale titles Three things found by actually using the app rather than measuring it. **Host was unusable.** The shell above a split view is overflow:hidden so the document cannot grow, which left anything taller than the viewport simply unreachable — and Host stacks a resources card, four stat cards and a tab bar above its split, so the bottom of the pane fell off at every window height with nothing to scroll. Every sweep I ran for this was horizontal, which is why it kept coming back clean. The page now scrolls inside the pinned shell. The pane keeps its own scroller: letting it grow instead pushes the document taller and stretches the rail to match, which is the regression e2e/discover-height.spec.js exists to catch, and which the first version of this fix duly caused. **The Agents header controls were unstyled** — "Create Agent" was rendering with the browser's default chrome. The markup had been mangled at some point: six unrelated classes merged into one string on the link, and the label and button left with none at all and empty icons. Repaired, with the inline flex replaced by a shared .header-actions class. **Page titles take the editorial scale from the site**: larger, tracked at -0.04em, on a line height near 1, so a two-word title reads as a statement rather than a label. The typeface is unchanged — DESIGN.md keeps the existing type system — so the whole difference is scale, tracking and leading, which is where the site gets its voice from. This was the biggest reason the running app still did not look like the mocks. Full e2e suite: 404 passed, 4 skipped. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5[1m] [Read] [Edit] [Bash] --------- 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
|
1189c6825b |
feat(tracing): persist bounded trace histories (#11203)
* feat(tracing): persist bounded trace histories Retain API and backend traces below the data path, restore them at initialization, and serialize clears with asynchronous consumers. Assisted-by: Codex:gpt-5 * fix(tracing): satisfy persistence security checks Document why persisted filenames cannot escape the trace directory and explicitly ignore the best-effort temporary-file cleanup result. Assisted-by: Codex:gpt-5 [golangci-lint] --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
Richard Palethorpe
|
49ef40a187 |
feat(classifier/VAD): support voice control on low power devices (#10804)
* feat(llama-cpp): route Score through the slot loop Score previously bypassed the slot loop with a direct llama_decode: a conflict guard aborted the whole process if scoring raced generation, the config validator had to reject score alongside chat/completion/embeddings, and every candidate re-decoded the full shared prompt. Add SERVER_TASK_TYPE_SCORE to the (patched) upstream server so score tasks are scheduled like any other slot work: generation and scoring serialize naturally, the shared prompt is decoded once per call, and the slot's prompt cache carries the conversation prefix across calls. Context checkpoints at the score boundary and at the cache-divergence point keep SWA/hybrid/recurrent models (e.g. LFM2.5) from re-prefilling the whole prompt per candidate: warm-turn scoring on a 6-option set drops from ~8s to ~0.5s on a desktop CPU. The conflict guard and the validation split are removed; declaring score with generation usecases on one config is now supported and shares the slot cache. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier wire types and pipeline config Wire types and YAML config for realtime classifier mode: sessions carry a localai_classifier extension (options with canned replies/tool calls, softmax threshold, normalization, history trimming, fallback modes, and a deterministic wake-word address gate), mirrored by pipeline.classifier in the model YAML and surfaced in the config-meta registry. The localai.classifier.result server event reports the full score distribution per turn. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier response flow Classifier-mode responses: instead of autoregressive generation, each user turn is prefill-scored against the option list (router.ScoreClassifier prompt/candidate shapes over the Score primitive) and the winning option's canned reply and tool call are emitted through the existing response machinery. Below-threshold turns take the configured fallback (none / canned reply / generate); empty transcripts and unaddressed turns (wake word not mentioned) skip scoring entirely. The scoring probe defaults to the latest user message only — small scorers echo canned replies from prior turns back as the top option otherwise. Built for hardware that can afford prompt processing but not decode: with slot-based Score the option list stays KV-cached across turns, so a turn costs roughly one forward pass over the new words. session_update_error events now carry the validation cause instead of a generic message. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): bound the VAD tick's scan window and buffer retention The VAD tick loop re-scanned the entire input buffer every 300ms and only trimmed it on zero-segment ticks or commits. Audio that keeps producing segments without a committing pause (steady noise a mic pipeline lets through, music, continuous speech) grew the buffer toward the 100MB cap with each tick rescanning all of it — O(n^2), measured at ~3.3ms of silero per buffered second: past ~90s retained, ticks run back to back and pin ~4 cores until the stream stops. Silero's recurrent state only carries a few hundred ms of context, so rescanning old audio buys nothing. Clip the slice handed to the VAD to the largest silence the commit test can need to measure (server_vad silence window or the semantic eagerness fallback) plus a warm-up margin, and rebase the returned segment times so every downstream consumer keeps whole-buffer coordinates. An open turn whose clipped window is all silence now commits (the silence outran the window) instead of being discarded as no-speech. Independently, retain at most 90s of raw buffer, rebasing the live-feed and EOU cursors on trim — this also bounds the previously unbounded VAD-error path. Turn boundaries are otherwise unchanged: no forced commits, no new coordinator states. pipeline.turn_detection.vad_window_sec can widen the scan window; values below the automatic floor are ignored. The tick body is extracted into vadTick so specs can drive turn detection synchronously (same shape as classifySoundWindow); the babble reproduction that pinned 4 cores now plateaus under 10% of one core. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(backend): let per-model threads override the global default ModelOptions overrode a set per-model threads value with the app-level --threads whenever the latter was non-zero — and WithThreads defaults it to the physical core count, so it always was. The YAML threads: knob has been dead config: a tiny VAD model could never opt down from the global pool size. SetDefaults already fills an unset per-model value from the app config, which is the intended precedence; resolve threads through a helper that honors it (explicit threads: 0 still means unset). Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(gallery): single-thread the silero VAD Silero is a ~2MB recurrent model with no exploitable graph parallelism: measured per-call latency is identical at 1 and 10 ORT threads, while every extra pool thread just spin-waits between the realtime loop's frequent tiny inferences. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * docs(realtime): classifier mode, VAD scan window, threads precedence Document the realtime classifier mode (options, threshold guidance, wake-word address gate, empty-transcript handling), the VAD scan window and 90s buffer retention (pipeline.turn_detection.vad_window_sec), the per-model threads precedence, and the M3 classifier note in the realtime state-machine design doc. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * perf(llama-cpp): score all candidates in one batched decode One scoring call is now a single SERVER_TASK_TYPE_SCORE task: the slot decodes the shared prefix (prompt + longest common candidate token prefix) once, then forks one sequence per candidate off it (metadata-only for the unified KV cache, copy-on-write for recurrent state) and decodes every candidate's unique tail in one llama_decode. Previously each candidate was its own task that restored the boundary checkpoint and re-decoded its full tail sequentially, paying per-candidate task and decode overhead. The context reserves SERVER_SCORE_FORK_SEQS extra sequence ids (and recurrent-state cells) beyond the parallel slots via the new common_params::n_seq_score_forks. Forking requires the unified KV cache (already this backend's default) since per-sequence streams would shrink n_ctx_seq; an explicit kv_unified:false disables forking and Score calls that need it fail cleanly. Candidates beyond the fork/output budget decode in successive chunks. Wire contract and scores are unchanged: per-token logprobs are stitched from the shared region and the forked tails. Verified bitwise deterministic call-to-call and independent of candidate order (no cross-fork leakage via equal-length candidate swap); ranking matches the per-candidate implementation on the drone battery (winner softmax 0.99996 vs 0.99997), and >16-candidate chunking, prefix-of-another and empty candidates all pass. Measured on a desktop CPU: warm /api/score calls 0.52s -> 0.23s; warm realtime classifier turns 196-303ms. The 9-candidate drone turn decodes ~17 unique tail tokens in one batch instead of nine sequential ~220ms checkpoint-restore tasks. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): gate scoring capacity by model usecase Reserve llama.cpp scoring slots only for models that explicitly declare the score usecase, while allowing score to coexist with chat and completion. Reject incompatible unified-KV settings and classifier activation on models without scoring capacity. Propagate application defaults when resolving realtime and preload pipeline stages so unset thread counts are resolved consistently without overriding explicit model settings. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): honor APT mirrors in the prebuilt llama-cpp compile step The builder-prebuilt path installs gcc-14 with apt directly and ignored the APT_MIRROR/APT_PORTS_MIRROR build args the from-source path already honors, so an ubuntu mirror outage broke every arm64 backend build. Pass the args into the stage and run apt-mirror.sh (already in the build context via COPY . /LocalAI) before the apt step. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier argument slots via constrained completion Hybrid classify-then-complete: a classifier option's canned tool call can declare typed argument slots (number | enum | string, with defaults and prompt hints) referenced as "{{name}}" in the arguments template. When the option wins, the slots are filled by a short grammar-constrained completion that continues the exact scoring prompt — rendered by the same cached ScoreClassifier, so the llama.cpp prompt cache is already warm — with the chosen route JSON re-opened at the first slot field. A GBNF grammar pins the field skeleton and frees only the values; temperature 0, a couple dozen tokens at most (~300ms on a desktop CPU for two slots). Slot declarations and hints ride the option descriptions in the shared system prompt, informing scoring and the fill alike at no per-turn token cost. The localai.classifier.result event carries the final arguments and a fill_latency_ms. On inference failure the slots' defaults apply; a slot without a default fails the response (or falls through with fallback.mode: generate). Slot filling requires completion alongside score in the scoring model's known_usecases. Verified end-to-end on the Pi drone demo: "fly forward three meters" in distance mode classifies forward and infers {"distance": 3, "units": "meters"} in ~310ms, and the drone flies exactly 3 units. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): splice filled slot values into classifier replies A classifier option's spoken reply can now reference its tool's argument slots ("Going forward {{distance}} {{units}}."): the values inferred by the slot-fill completion — or the recovery defaults — are spliced into the reply as plain text before it is emitted, so what the assistant says confirms what it actually inferred. Placeholders without a value stay literal, and options without slots are untouched. FillToolArguments now returns the raw slot values alongside the spliced arguments JSON to make the reply templating possible. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): harden classifier slot completion Reserve context for constrained slot filling, size completions from their encoded output, and encode enum grammar literals as valid JSON. Reject empty enum values and cover the failure modes with regression tests. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): prewarm the classifier scoring prompt on registration Swapping a session's classifier option list (a voice-switched command mode, for instance) made the next turns pay a full re-prefill of the new option-list prompt — measured 2.4s vs 0.3s warm on a desktop CPU, and worse: on hybrid-memory models like LFM2.5, whose state cannot be partially rewound (llama.cpp can only restore checkpoints), *every* probe change re-prefilled from scratch whenever the last checkpoint missed the probe boundary, so even same-list turns intermittently cost full prefills. Registering an option list (pipeline seed or session.update) now fires a best-effort background prewarm: two throwaway scores with distinct probes. The first prefills the new option-list prompt; the second, diverging exactly where per-turn probe text starts, plants the backend's rewind point (KV checkpoint) at the stable-prefix boundary that every real turn reuses. The prewarm hides behind the canned mode-switch reply — by the time it finishes speaking, the cache is warm. Idempotent per option set, detached from the registering request's lifetime. Measured on the drone demo (LFM2.5-1.2B, desktop CPU): first turn after a mode switch 2374ms -> 340ms; intermittent same-list full prefills (1.3-2.1s) all -> under 0.5s. For clients that swap lists frequently, options: [parallel:2] on the scoring model additionally keeps one slot per list via prefix-similarity routing (+26MB RSS, unified KV). Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * perf(llama-cpp): checkpoint scoring at the caller-declared stable prefix Hybrid-memory models (LFM2.5 shortconv, Qwen3.5 deltanet — where new small models are headed) cannot rewind their state, so any prompt-cache reuse that needs a rewind falls back to a full re-prefill. For classifier scoring that meant every probe change re-processed the whole option-list prompt: the server's checkpoints were placed reactively (at wherever the previous task happened to diverge), so a checkpoint past the next divergence was erased rather than restored — measured as intermittent 2-10s turns on prompts with a 95%+ common prefix. The classifier now computes the probe-invariant prompt prefix once (the byte-wise common prefix of two synthetic probe renders) and declares its length with every Score request; the server maps it to a token boundary and forces a KV checkpoint exactly there on each score prefill. That checkpoint sits at or before every future divergence under the same option list, so it always survives and always restores — repeat scoring costs probe+candidates regardless of how the probe changes. Also: - prewarm reruns on every option-list registration instead of memoizing per list: with boundary checkpoints a redundant rewarm costs two probe-sized decodes, while skipping one after a slot eviction (three lists sharing fewer slots evict in LRU cascades) silently moves a full re-prefill onto the user's next turn - new llama.cpp backend option rs_seq:N exposes bounded recurrent-state rollback outside speculative decoding; measured impractical for deltanet-scale states (65GB for 64 snapshots on Qwen3.5-4B) but cheap insurance for small-state models - docs: the multi-list recipe (parallel:N + sps:0.5 — the default slot similarity threshold funnels distinct lists onto one slot) Measured on the drone demo (LFM2.5-1.2B scorer, desktop CPU), steady state: every turn 285-421ms including mode switches, vs 2.4s post-switch and intermittent 1.3-2.9s re-prefills before. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): align classifier cache guidance Document the single-score prewarm behavior and clean the vendored score patch formatting. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(llama-cpp): guard score task for fork backends TurboQuant and Bonsai reuse the primary gRPC server against llama.cpp forks that do not carry LocalAI's slot-based Score patches. Compile the Score integration only for the patched primary backend and return UNIMPLEMENTED from fork builds instead of referencing absent task types and common_params fields. Assisted-by: Codex:gpt-5 [gh] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(dev): generate gRPC code before commit lint The coverage phase regenerates ignored protobuf bindings, but lint runs first and can fail against missing or stale output. Generate the pinned bindings before lint so the gate always type-checks the current schema. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
ff299df453 |
perf(http): gzip responses, cache hashed assets, bound the trace endpoints (#11056)
Three measured HTTP-layer regressions on a live deployment, fixed together
because they all shape the bytes on the wire.
1. No compression. The server sent no Content-Encoding regardless of what
the client asked for, confirmed with curl straight at 127.0.0.1:8080 so
it was not an ingress artefact. Adds gzip middleware, on by default and
configurable via LOCALAI_DISABLE_HTTP_COMPRESSION and
LOCALAI_HTTP_COMPRESSION_MIN_LENGTH (default 1024 bytes so tiny bodies
are not wastefully wrapped). Streaming routes are skipped explicitly:
an SSE Accept header, a WebSocket upgrade, and the completion / SSE /
log-tail path prefixes, because whether a completion request streams is
decided by the request body, which the middleware runs too early to see.
Already-compressed formats (woff2, png, mp4, ...) are skipped too; gzip
made those marginally larger. Measured over the embedded React build:
JS+CSS 2815 KB raw to 808 KB gzipped (3.48x).
2. No cache headers on content-hashed assets. Vite hashes the filenames,
so a given /assets/ URL can never change content, yet they shipped with
no Cache-Control, ETag or Last-Modified, and the browser re-fetched the
whole bundle on every navigation with no conditional request available.
/assets/* now carries public, max-age=31536000, immutable. index.html
stays no-cache so a deploy is picked up, and the unhashed locale JSONs
get a short TTL rather than the immutable one.
3. Unbounded trace endpoints. /api/traces returned 21,033,606 bytes in
4.65s and /api/backend-traces 3,471,682 bytes in 1.50s, and the admin
UI polls both every few seconds. The ring buffer holds up to 1024
entries, each embedding full input_text payloads. Both list endpoints
now take limit / offset / full, default to 50 entries, and strip the
heavy fields (request and response bodies plus headers for API traces,
body and data for backend traces) unless full=true. Every trace gets a
process-lifetime ID and GET /api/traces/{id} and
/api/backend-traces/{id} serve the full record, which is what the UI
fetches when a row is expanded. The list body stays a JSON array;
paging metadata rides in X-Total-Count, X-Trace-Offset and
X-Trace-Limit. Reproducing the live shape in a test, the polled payload
goes from 21,131,097 bytes to 7,201 bytes.
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
localai-org-maint-botandEttore Di Giacinto
|
4be6e22b5f |
feat(webui): surface user, client IP and user agent in API traces (#10886, #10887) (#10907)
The Operate → Traces "API Traces" panel already recorded who made each request (user_id/user_name) but never showed it, and did not capture the caller's network identity at all. Operators asked to see the requesting user (#10886) and the client IP + user agent (#10887) so a trace can be attributed to who/what issued it. Backend: add ClientIP and UserAgent to APIExchange and populate them from echo's c.RealIP() (honours X-Forwarded-For / X-Real-IP behind a trusted proxy) and the request's User-Agent header. Both are omitempty and the /api/traces swagger response is map[string]any, so this is additive. UI: add a sortable "User" column to the API traces table and a metadata block (User / Client IP / User Agent) at the top of the expanded row detail. Fields render only when present, so older buffered traces and unauthenticated/local requests degrade cleanly. Adds an e2e spec covering the new column value and the expanded metadata. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
fe4f425fb5 |
fix: correct scheme/host on self-referential URLs behind an HTTPS reverse proxy (#10482) (#10504)
* fix(http): harden BaseURL proxy scheme/host detection Split comma-separated X-Forwarded-Proto and honor the RFC 7239 Forwarded header so generated links use https behind common reverse-proxy setups. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(http): honor explicit external base URL in BaseURL When _external_base_url is set in the request context it dictates the origin (scheme+host+port); the proxy path prefix is still appended. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(config): generalize LOCALAI_BASE_URL to ExternalBaseURL LOCALAI_BASE_URL now sets a single instance-wide external base URL used for OAuth callbacks and all self-referential links. A Pre middleware stamps it into the request context for middleware.BaseURL. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: document LOCALAI_BASE_URL and reverse-proxy headers Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(http): cover parseForwarded edge cases; clarify base-url flag group Adds direct unit coverage for quoted/malformed/multi-element Forwarded headers and regroups the external base URL flag away from auth-only. Refs #10482 Assisted-by: Claude:claude-opus-4-8 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 [bot]andEttore Di Giacinto
|
9565db5f94 |
feat(models): model aliases - redirect a model name to another configured model (#10414)
* feat(config): add model alias field and self-validation Add ModelConfig.Alias (yaml: alias), IsAlias(), and an alias short-circuit at the top of Validate() that rejects self-reference and forbids setting backend/parameters.model on a pure-redirect alias. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(config): resolve and validate model alias targets in the loader Assisted-by: Claude:opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(middleware): resolve model aliases and stamp requested/served identity Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(modeladmin): reject alias configs with invalid targets on create/edit Validate alias targets at create/swap entry points (ImportModelEndpoint, EditYAML, PatchConfig) so a dangling, chained, or disabled alias target is rejected at save time rather than surfacing as a runtime error. Assisted-by: Claude:opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(api): add GET /api/aliases to list model aliases Adds an admin-gated read-only endpoint that lists every model alias config as {name, target} pairs, backed by the loader's existing GetAllModelsConfigs(). Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(mcp): add set_alias and list_aliases tools Expose model-alias management over the LocalAI Assistant MCP surface: list_aliases (read-only, GET /api/aliases) and set_alias (mutating). SetAlias is swap-first: PATCH /api/models/config-json/:name swaps an existing alias's target (validated, non-destructive) and a 404 falls back to POST /models/import to create a fresh {name, alias} config. The inproc client mirrors this via ConfigService.PatchConfig + a create path modeled on ImportModelEndpoint. Deletion reuses delete_model. Assisted-by: Claude:claude-opus-4 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(mcp): replace em dashes in alias tool comments Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(config-meta): expose alias as a model-select field Add an 'alias' section to DefaultSections() and an 'alias' field override in DefaultRegistry() so the schema-driven React editor renders the new top-level ModelConfig.Alias field as a model picker in its own section. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): add alias template card and Manage alias badge Add an 'Alias / Routing' template to the create-flow gallery that seeds a minimal name + alias config, and a read-only 'alias -> target' badge on the Manage Models tab. The capabilities row payload does not carry the alias field, so the badge resolves targets from GET /api/aliases looked up by name. Assisted-by: Claude:claude-opus-4 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: document model aliases Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(swagger): regenerate for GET /api/aliases Adds the /api/aliases path and AliasInfo schema generated from the ListAliasesEndpoint annotation. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(localai): check os.RemoveAll error in aliases_test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: correct alias conversion docs and advertise /api/aliases in instructions Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(mcp): write alias config 0600 to satisfy gosec G306 The inproc createAlias path wrote the alias YAML with 0644, which gosec flags as a new G306 finding on the PR. The LocalAI process is the sole reader/writer of model configs, so 0600 is correct and keeps the scan clean. Assisted-by: Claude:claude-opus-4-8 [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> |
||
|
Richard Palethorpe
|
3fa7b2955c |
feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)
Squashed feat/pii-ner-tier-engine rebased onto master (was 45 commits; see backup/pii-ner-tier-engine-prerebase). Net change: - privacy-filter.cpp: standalone GGML engine for the openai-privacy-filter PII/NER token classifier, wired as a LocalAI gRPC backend (CPU/CUDA/Vulkan). TokenClassify moves off the patched llama.cpp path onto this backend. - PII filter reworked to be NER-centric (encoder/NER detection tier scanning whole conversations as one document), with a recreated bounded restricted- regex secret-matching pattern detector tier alongside it (per-model pii_detection.builtins / .patterns + core/services/routing/piipattern). - Detection labelled by source (ner vs pattern); backend trace / confidence / debug observability; analyze/redact exposed as a synchronous API. - Instance-wide default detector policy + per-usecase default-on; request filtering extended to completions, embeddings, edits & Ollama. - React UI: NER-centric PII editor, detector-models table, pattern/builtins editor, middleware default-policy UI. - Gallery: privacy-filter-multilingual token-classify model + NER install filter; token_classify known_usecase; batch sized to context for NER models. privacy-filter backend registered in the backend gallery (cpu/vulkan/cuda-13 meta + image entries with a capabilities map) matching its CI matrix jobs, and an /import-model auto-detect importer (PrivacyFilterImporter, narrow privacy-filter GGUF detection) replacing the prior pref-only registration. Reconciled against master's independent evolution: - Dropped master's PIIPatternOverrides feature (global-pattern runtime overrides + /api/pii/patterns API + runtime_settings.json persistence). The per-model NER + pattern-detector design supersedes it; it was built on the global redactor pattern set this branch replaced. - Reverted the llama.cpp Score carry-patch (0006-server-task-type-score): removed the patch and restored master's grpc-server.cpp Score RPC (direct llama_decode, slot-loop bypass) and LLAMA_VERSION pin, plus master's model_config validation forbidding score + chat/completion/embeddings on llama-cpp. token_classify is unaffected (it runs on the privacy-filter backend, not llama-cpp). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
1ab61a0875 |
feat: generic chat_template_kwargs (model config + per-request metadata) (#10359)
* feat(config): add chat_template_kwargs model field + resolver Adds the ChatTemplateKwargs model-config map and RequestMetadata carrier, plus ResolveChatTemplateKwargs which layers the config map under coerced request metadata. Foundation for generic jinja chat-template kwargs (issue #10329). Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(backend): forward resolved chat_template_kwargs blob to backends gRPCPredictOpts now merges per-request client metadata over the server-derived enable_thinking/reasoning_effort (reaching all backends via the standalone keys) and serialises the resolved chat_template_kwargs map into a JSON blob for llama.cpp, written last so a client cannot clobber it. Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(http): wire request metadata to config.RequestMetadata The OpenAI request metadata field was parsed but unused; stamp it onto the per-request ModelConfig so gRPCPredictOpts forwards it as chat_template_kwargs overrides. Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(llama-cpp): generic chat_template_kwargs merge (drop per-key blocks) Replace the per-key enable_thinking/reasoning_effort handling in both the streaming and non-streaming chat paths with a single block that parses the chat_template_kwargs JSON blob resolved by the Go layer and merges every key into body_json. New jinja template levers (e.g. preserve_thinking) now need no C++ change. Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: document custom chat_template_kwargs (model + per-request) Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(backend): pin reasoning_effort as a string in the chat_template_kwargs blob Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(http): e2e guard pinning chat_template_kwargs forwarded to gRPC Adds an ECHO_PREDICT_METADATA marker to the mock-backend that echoes the received PredictOptions.Metadata, and an app_test.go spec that drives a real /v1/chat/completions request (model chat_template_kwargs + per-request metadata override) and asserts the exact metadata + chat_template_kwargs blob the REST layer forwards to gRPC. Locks the REST->gRPC contract against regressions. Issue #10329. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(config): grandfather chat_template_kwargs in registry coverage chat_template_kwargs is a free-form map[string]any (like engine_args, already on the list), not a scalar the config UI registry can surface, so it is exempt from the registry-entry requirement. Fixes the TestAllFieldsHaveRegistryEntries failure introduced by the new field. Issue #10329. Assisted-by: Claude:claude-opus-4-8 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> |
||
|
Richard Palethorpe
|
085fc53bbc |
fix(router): production-ready request router + auto-size batch for embedding/rerank (#10104)
* fix(router): score classifier production-readiness Conversation trimming runs through the classifier model's chat template and trims by exact token count, sized to the model's n_batch which is now scaled to context so long probes can't crash the backend. Missing chat_message templates are a hard error at router build time. Router- facing factories (Embedder/Scorer/Reranker/TokenCounter) re-resolve ModelConfig per call so a model installed post-startup doesn't bind a stub Backend="" config and silently fall into the loader's auto- iterate path. New 'vector_store' backend trace recorded inside localVectorStore on every Search/Insert — including the backend-load-failure path that previously vanished into an xlog.Warn — with outcome tagging (hit/miss/empty_store/backend_load_error/find_error/insert_error/ok). Companion cleanup drops misleading similarity:0 and input_tokens_count:0 from non-hit and text-mode traces. Gallery local-store-development aliases to 'local-store' so the master image satisfies pkg/model.LocalStoreBackend lookups from the embedding cache. Misc: llama-cpp TokenizeString reads the correct 'prompt' JSON key (the original bug); ModelTokenize nil-guard; non-fatal mitm proxy startup; PII 'route_local' renamed to 'allow' with docs/UI in sync; model-editor footer no longer eats the edit area on small screens; several config-editor template/dropdown/section fixes. Tests: e2e router specs (casual/code-hint + long-conversation trim), vector_store trace specs, lazy-factory specs, gallery dev-alias resolution, Playwright trace badge + scroll regression. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(backend): auto-size batch to context for embedding and rerank models Embedding and rerank models pool over the whole input in a single physical batch (n_ubatch). With batch left at the 512 default, the backend rejects longer inputs with "input is too large to process", silently capping a large-context embedder (e.g. 8k/32k) at 512 tokens. Size n_batch to the context for these single-pass usecases, mirroring the existing FLAG_SCORE behaviour; an explicit batch: still wins. Extracts EffectiveContextSize/EffectiveBatchSize from grpcModelOpts so the effective decode window has one home for other callers to reuse. Adds an e2e-aio regression test that embeds a >512-token input. The AIO embedding model is switched to nomic-embed-text-v1.5 (2048 context) because the previous granite model was capped at 512 tokens and could not exercise the larger batch. Assisted-by: claude-code:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(gallery): raise arch-router scoring output cap via parallel:64 Scoring decodes the whole prompt+candidate in a single llama_decode and reads one logit row per candidate token. The vendored llama.cpp server caps causal output rows at n_parallel, so the default of 1 aborts with GGML_ASSERT(n_outputs_max <= cparams.n_outputs_max) on multi-token route labels. Set options: [parallel:64] on both arch-router quant entries to lift the cap; kv_unified (the grpc-server default) keeps the full context per sequence, so this does not split the KV cache. Assisted-by: claude-code:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
e837921c2c |
feat: forward reasoning_effort to the backend so jinja models honor it (#10184)
* feat: forward reasoning_effort to the backend so jinja models honor it reasoning_effort was only mapped to the binary enable_thinking toggle and otherwise reached Go-side templates — it was never sent to the backend. So jinja-templated models whose chat template keys on reasoning_effort (gpt-oss Harmony, LFM2.5) could not be driven by it: LFM2.5 ignores enable_thinking and kept emitting <think>. Forward the effective reasoning_effort to the backend as a chat_template_kwarg (mirroring enable_thinking) in grpc-server.cpp, and put it in PredictOptions metadata (gRPCPredictOpts). Add a config-level default: ModelConfig.reasoning_effort and Pipeline.reasoning_effort, resolved by ModelConfig.ApplyReasoningEffort (request value overrides config default, none->disable / level->enable, an operator's reasoning.disable wins). request.go now uses that helper. Assisted-by: Claude:claude-opus-4-8 go test, golangci-lint Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): set the pipeline LLM's reasoning_effort Apply Pipeline.ReasoningEffort to the pipeline's LLM config when the realtime model is built (per-session copy, overrides the LLM's own reasoning_effort), and surface the resolved effort on the template input so Go-templated models get it too. jinja models receive it via the backend metadata. This lets a realtime pipeline disable thinking on models that only honor reasoning_effort (e.g. LFM2.5), which enable_thinking can't. Assisted-by: Claude:claude-opus-4-8 go test, golangci-lint 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> |
||
|
Richard Palethorpe
|
718223f33b |
feat(localvqe/audio): v1.3 release and add spectrograms to audio transform UI (#10113)
* chore(localvqe): update backend to v1.3, add v1.2/v1.3 gallery models Bump the LocalVQE backend pin 72bfb4c6 -> b0f0378a, which adds the v1.2 (1.3 M) and v1.3 (4.8 M) GGUF SHA-256s to the upstream released-models allowlist (and the arch_version=3 loader) so both load without LOCALVQE_ALLOW_UNHASHED. Add gallery entries for localvqe-v1.2-1.3m and localvqe-v1.3-4.8m (SHA-256 verified against the downloaded weights) and update the audio-transform docs to make v1.3 the current default while noting the compact v1.1/v1.2 alternatives. Assisted-by: Claude:claude-opus-4-8 Claude-Code Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(flake): add ffmpeg-headless to the dev shell pkg/utils/ffmpeg_test.go shells out to the `ffmpeg` CLI, and the pre-commit gate runs those tests via `make test-coverage`. Without ffmpeg in the dev shell the gate fails with "executable file not found in $PATH". The headless build provides the CLI without GUI/X deps. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(localvqe): parse WAV by walking RIFF sub-chunks Walk the RIFF chunk list instead of assuming the canonical 44-byte header layout. Real inputs (browser-recorded clips, ffmpeg output with an 18/40-byte extensible `fmt ` chunk or trailing LIST/INFO metadata) would otherwise splice header/metadata bytes into the PCM stream as an audible impulse. Honour the `data` chunk size and validate that both `fmt ` and `data` chunks are present. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(security-headers): allow blob: in connect-src for waveform fetch The waveform renderer XHRs/fetches a freshly-created blob: object URL (e.g. an uploaded or enhanced clip before it has a server URL). XHR/fetch of blob: is governed by connect-src, not media-src, so it was blocked by the CSP. Add blob: to connect-src. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(react-ui): add input/output spectrogram view to AudioTransform The transform page only showed time-domain amplitude waveforms, so you could see how loud a clip was but not which frequencies the model touched. Add a time x frequency spectrogram heatmap and render the input and output spectrums side by side, so it's visible which bands the enhancement attenuates (bright input bands that go dark in the output). Computed client-side via a Hann-windowed STFT over both clips (a small dependency-free radix-2 FFT), defaulting to the LocalVQE 512/256 frame geometry. This shows the net input->output spectral change; the model's internal gain mask is not exposed by the backend. - src/utils/fft.js radix-2 FFT - src/hooks/useSpectrogram.js decode + STFT -> normalised dB magnitude grid - src/components/audio/Spectrogram.jsx canvas heatmap (magma colormap) - AudioTransform.jsx dual-spectrogram panel + CSS - e2e spec + UI coverage baseline bump (38.29 -> 39.0; measured ~39.4-40.2) Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * test(react-ui): make UI coverage deterministic, tighten the gate UI e2e line coverage swung ~1pp run-to-run (39.1% <-> 40.2%), which forced a loose 0.8pp tolerance on the monotonic gate — a band wide enough to let a real ~300-line regression through silently. The swing was a bug, not inherent jitter: the 'Create Agent navigates' spec ended on the URL assertion, so AgentCreate.jsx's ~400 lines were collected only when its render happened to beat the coverage teardown. Wait for the page to actually render (assert its heading) so those lines are covered every run. With the race gone, repeated runs land within ~0.013pp of each other, so: - tighten UI_COVERAGE_TOLERANCE 0.8 -> 0.1 (noise floor, not a drift band) - set the baseline to the real, reliably-achieved value (39.0 -> 39.86) Localised by running the V8-coverage suite repeatedly and diffing per-file line coverage; AgentCreate.jsx was the sole ~1pp flipper. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
4a2cc64d07 |
feat(reasoning): honor per-request reasoning_effort on chat completions (#10082)
The OpenAI `reasoning_effort` field only reached the prompt template; it never toggled the backend's thinking. Map it onto ReasoningConfig.DisableReasoning (which becomes the enable_thinking gRPC metadata) in the request merge, so reasoning_effort="none" disables reasoning per request: the use case from #10072 (run a single Qwen3-style model and turn reasoning off for low-latency tasks while keeping it on for others). Effort levels (minimal/low/medium/high) enable thinking unless the model config explicitly disabled it (reasoning.disable: true wins and is never re-enabled by a request); "none" always disables. Closes #10072 Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
06e777b75e |
feat(distributed): gated X-LocalAI-Node response header (middleware + wrapper) (#9976)
* feat(distributed): add per-request node ID context holder Introduce pkg/distributedhdr, a leaf package carrying a per-request *atomic.Value holder for the picked worker node ID from the SmartRouter (core/services/nodes) up to the HTTP response writer wrapper (core/http/middleware). Avoids the import cycle that a shared key in either consumer would create. Exposes NewHolder, WithHolder, Holder, Stamp, Load, Inherit. The holder is atomic.Value so cross-goroutine publish from the router to the response writer wrapper is race-clean. Assisted-by: Claude:claude-opus-4-7[1m] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): add ExposeNodeHeader middleware + response writer wrapper New ApplicationConfig.ExposeNodeHeader bool + --expose-node-header CLI flag / LOCALAI_EXPOSE_NODE_HEADER env var (default off; the node ID reveals internal topology and is opt-in). The middleware creates a per-request *atomic.Value holder, attaches it to c.Request().Context() via distributedhdr.WithHolder, and wraps c.Response().Writer with a custom http.ResponseWriter that sets the X-LocalAI-Node header on first Write / WriteHeader / Flush by reading the holder. Implements http.Flusher, http.Hijacker, Unwrap so it composes cleanly with Echo and http.NewResponseController. request.go propagates the holder onto derived contexts via distributedhdr.Inherit so the holder survives the correlation-ID context replacement. Unit + race-clean concurrency + integration specs. Assisted-by: Claude:claude-opus-4-7[1m] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): stamp node ID in router and wire middleware to inference routes ModelRouterAdapter.Route stamps the picked node ID into the per-request holder via distributedhdr.Stamp(ctx, result.Node.ID) right after replica selection. Wire ExposeNodeHeader middleware to: - OpenAI chat/completion/embeddings + audio transcriptions/speech + image generations/inpainting - Anthropic /v1/messages - Ollama /api/chat, /api/generate, /api/embed, /api/embeddings - Jina /v1/rerank - LocalAI /v1/vad The middleware's wrapper reads the holder on first byte and sets the X-LocalAI-Node response header before delegating to the underlying writer. Per-request scope means no race under concurrent multi-replica routing. Assisted-by: Claude:claude-opus-4-7[1m] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): thread request context through backend Load + cover ctx propagation Five non-OpenAI backend helpers were silently using app.Context instead of the request context for the gRPC backend call: transcription, TTS, image generation, rerank, VAD. Effect: distributedhdr.Stamp in the router callback was a silent no-op for these paths, AND client cancellation didn't propagate to in-flight inference. Thread c.Request().Context() (or the equivalent input.Context after the request middleware has installed the correlation-ID derived context) through each helper and into ModelOptions via model.WithContext(ctx). ImageGeneration's signature gains a leading ctx parameter; in-tree callers (openai image, openai inpainting, openai inpainting_test) are updated to match. ModelEmbedding gains a leading ctx parameter for the same reason; the openai and ollama embedding handlers pass the request context through. chat_stream_workers.go defers the initial role=assistant chunk emission until the first token callback so the wrapper's lazy X-LocalAI-Node lookup against the loader runs AFTER ml.Load has stamped the per-modelID node ID; semantically identical for clients (role still arrives before any text). Regression test core/backend/ctx_propagation_test.go pins ctx propagation for all five helpers. Docs updated to enumerate the full endpoint coverage of the --expose-node-header flag. Assisted-by: Claude:claude-opus-4-7[1m] 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> |
||
|
Richard Palethorpe
|
6a80e23733 |
feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)
Add a routing middleware stack and a cloud-proxy backend. * cloud-proxy: a Go gRPC backend that forwards OpenAI- and Anthropic-shaped chat requests to upstream providers, with an optional translate mode (OpenAI request -> Anthropic /v1/messages -> OpenAI response) and full tool-calling support. * routing: admission control, content-aware model routing (embedding cache + classifier + rerank + Arch-Router score), PII detection/redaction (regex + NER) with streaming filter and OpenAI/Anthropic adapters, and a per-user/per-key billing recorder backed by GORM or in-memory storage. * middleware: UsageMiddleware records usage via the billing recorder, plus admission, route-model, usage-stamp and trace middlewares. * observability: BackendTrace ring buffer stores full request bodies (capped), MITM proxy emits structured trace events, and router classifier decisions surface at /api/router/decide. * gallery: Arch-Router-1.5B (Q4_K_M and Q8_0). * UI: cloud-proxy model-editor fields, classifier system-prompt and score-normalization config, and a Traces page rendering request bodies. Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash] Signed-off-by: Richard Palethorpe <io@richiejp.com> |