mirror of
https://github.com/mudler/LocalAI.git
synced 2026-11-03 11:04:53 -05:00
2676dcafe8e543ff5135b685458a09bcb901bbc3
48
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 mudler-agent
|
cd604b5c5b |
fix(distributed): bound, stop and cancel model loads with leases and worker operations (#12524)
Fence model load jobs by generation, lease them on the database clock, bound the work on the worker with operations and a process-group watchdog, and add one stop path with a load-cancel API. See the pull request for the design, the rolling upgrade notes and the test evidence. Assisted-by: Claude Code:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler-agentandEttore Di Giacinto
|
e4fa051ee3 |
refactor(distributed): put the NATS-only paths behind interfaces (#12395)
* feat(messaging): add shared subject rules Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(messaging): cover BroadcastRoots, ControlRoots and SubjectRoot Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): add Broadcaster and enforce subject rules in every carrier Broadcaster is the fan-out half of MessagingClient. The NATS client and the in-memory FakeBus now refuse a subject outside the served roots and any wildcard other than a whole single token, and FakeBus shares MatchSubject instead of its own copy. FakeBus Unsubscribe now removes its own subscription instead of the first one with the same subject. A shared conformance suite in messagingtest runs against both carriers. The distributed e2e specs that used invented test.* subjects, and the one that subscribed with a > filter, now use subjects from subjects.go. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: depend on Broadcaster where only publish and subscribe are used Narrowed to messaging.Broadcaster: nodes/staging_progress.go, nodes/install_progress_publisher.go, galleryop/operation.go, galleryop/service.go, agentpool/user_services.go, agentpool/agent_jobs.go, openresponses/store.go, openresponses/sync.go, syncstate/syncstate.go, finetune/service.go, quantization/service.go and failover/distsync/distsync.go. SubscribeJSON now takes a Broadcaster because it only calls Subscribe, which lets the narrowed consumers use it. Stayed wide: worker/supervisor.go, because its client field also serves the SubscribeReply handlers in worker/lifecycle.go. The request/reply, queue and wiring files (nodes/unloader.go, nodes/file_stager_s3.go, jobs/dispatcher.go, agents/dispatcher.go, agents/events.go, worker/file_staging.go, cli/agent_worker.go, http/app.go) are unchanged by design. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): name the no-route condition and confine the carrier error Consumers matched nats.ErrNoResponders, which names an absence, to demote a node. They now match ErrNoRoute, the control path maps the carrier's failure onto it, and timeouts and worker refusals are pinned as not being no-route. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(nodes): state which FileStager implementations return ErrNoRoute Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): build backend clients through one node-aware seam Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: describe the distributed transport seams Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: correct comments that overclaim after the seams refactor Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(agent-worker): refuse an unserved LOCALAI_AGENT_SUBJECT at startup The messaging client now refuses a subject whose root no carrier serves. An agent worker started with a custom LOCALAI_AGENT_SUBJECT such as tenant-a.agent.execute used to start and then wait on a subject the frontend never publishes to. After the subject rules landed it exited at subscribe time with an error that did not name the setting. Behaviour change: the worker now checks LOCALAI_AGENT_SUBJECT before it registers or connects, and exits with an error that names the variable and says to use a served subject under the agent root, for example agent.execute. The served roots are not widened: a custom root was never delivered by the frontend, and a wider set would reopen the drift the subject rules exist to close. The flag help and the agent worker docs state the constraint. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(nodes): pin the reactions to ErrNoRoute Three callers react to ErrNoRoute and had no spec: the reconciler's upgrade drain falls back to the legacy forced install, the reconciler marks the node unhealthy when a pending op has no route, and the backend-op fan-out marks the node unhealthy. Each spec drives the real caller with a scripted no-responders reply and reads the result from the registry or the recorded requests. A fourth spec pins the other side: a pending op that times out leaves the node healthy and only counts the attempt, so mapping timeouts onto ErrNoRoute would fail here. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(messaging): pin client subject checks and fail the carrier suite in CI Add specs that call Publish, Request, Subscribe, QueueSubscribe, SubscribeReply and QueueSubscribeReply on a client with no connection. Each call must return ErrUnservedSubject for bogus.thing and ErrUnsupportedWildcard for jobs.>. This proves that the subject check runs before the connection is used, and needs no server. The NATS conformance suite is the only check that runs the subject rules against a real carrier. Before this change it skipped without output when Docker was missing. Now it fails when CI is set, so a Linux runner without Docker cannot hide it. It still skips on local runs and on macOS CI, which has no Docker. Add SubjectNodeBackendInstallProgress to the list of constructors that must build served subjects, and ask contributors to extend the list. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: state what ErrNoRoute may change, and group the distributed guides The seams note said MarkUnhealthy was the only state change allowed on ErrNoRoute. A pending backend op still records the failed attempt, counts toward the reconciler's retry limit and is dead-lettered after the maximum attempts. The note now says that MarkUnhealthy is the only change to the node's own state, and that the per-op accounting is not a verdict about the node. The note also documents that the NATS conformance run fails under CI when Docker is missing. The distributed-seams row moves next to the distributed-state row in the topics table. The liveness ping spec header now says no route is a reason to skip the worker, not proof that the worker is gone. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): give the backend client factory the node id Mechanical: the method gains a nodeID parameter and the eight test fakes are updated. No behaviour change. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): drop the optional node-aware factory The node id is now in the main method, so the optional interface and its helper had no behaviour of their own. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): dial backend probes through the client factory Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): dial workers' file servers through a per-node dialer Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(http): proxy backend logs through the per-node worker dialer The admin backend-logs proxy (list, lines and the WebSocket stream) now reaches a worker through the same per-node dialer as the HTTP file stager, so every frontend-to-worker dial goes through one seam. The shared direct dialer keeps alive for 15s where the proxy used 30s. Harmless for requests bounded at 15s. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(http): keep the backend-logs proxy independent of the admin connection The proxy request had no context before the dialer change and is bounded only by its 15s timeout. Keep it that way. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: move the worker control payloads to workerctl Mechanical move of the request and reply structs, the install progress event and the file payloads out of messaging. The verbs no longer belong to one carrier. No alias is left behind. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(worker): serve the lifecycle verbs through a controlServer The worker registers one handler per verb and a NATS server maps each verb to its subject. Registration errors now name the verb. node.stop is served with SubscribeReply, which is identical on the wire because the handler never replies. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(worker): report install progress through the control sink Install and upgrade now emit download progress through the sink the control server hands them. The debounce and the terminal flush stay in the handler path, built over that sink by the new nodes.NewDebouncedInstallProgressSink, which replaces NewDebouncedInstallProgressPublisher. The subject and payload on the wire are unchanged. The supervisor no longer holds the bus, and installFn and upgradeFn let specs drive both verbs without a gallery. The malformed-request log lines are restored for install, upgrade, backend.delete, model.unload, model.stop and model.delete, with the reply bytes unchanged. The signal adapter is renamed noReply, which also lets worker.go import os/signal without an alias again. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(worker): serve the file-staging verbs through a controlServer An empty list-dir answer is now {} rather than {"files":null}, because the typed reply omits an empty Files slice. The frontend decodes both to a nil slice in nodes/file_stager_s3.go. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): add WorkQueue and the NATS producer This is the producer side of the competing-consumer seam. The work kinds map one to one to today's subjects and queue groups: task to jobs.new and mcp-ci to jobs.mcp-ci.new (both in group workers), agent-run to agent.execute (group agent-workers). Enqueue publishes the payload as Publish does today, with one JSON marshal. FakeBus now records queue groups and keeps reply handlers so later specs can pin and drive them. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): add the NATS WorkConsumer An in-flight limit of one runs the handler inline on the delivery goroutine, as the MCP CI consumer does today. Any other limit spawns per delivery, as the agent consumer does. Queue groups are unchanged. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: publish queued work through WorkQueue The job dispatcher, the agent pool and the agent scheduler enqueue through messaging.WorkQueue; the NATS implementation publishes to the same subjects as before. DistributedServices builds the queue next to the NATS client and hands it to the dispatcher and the agent pool, whose distributed mode switch now reads a non-nil WorkQueue. The unused AgentPoolService.SetNATSClient is removed. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: consume queued work through WorkConsumer The agent dispatcher and the MCP CI consumer register through messaging.WorkConsumer. The NATS implementation keeps the inline one-at-a-time model for MCP CI and the per-delivery model for agent runs. handleMCPCIJob reports on the events publisher the carrier hands it instead of a captured client. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: delete the consumers nothing in production reached jobs.new has a producer and no production consumer, and the agent dispatcher's Dispatch was only called from tests. Publishing jobs.new is unchanged. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(mcp): send MCP requests to agent workers through AgentControl Timeouts still honour only the deadline, not cancellation, exactly as today. The NATS no-responders error maps to ErrNoRoute and a timeout does not. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(agent-worker): serve MCP requests and backend.stop through agentRPCServer The agent worker's MCP tool and discovery reply subscriptions and its backend stop listener move behind an unexported agentRPCServer interface, served on NATS by nodes.NATSAgentRPCServer. The handlers become typed mcp.ToolHandler and mcp.DiscoveryHandler values that answer every failure with a reply carrying Error. Queue group (agent-workers), inline execution on the delivery goroutine, the background handler context, the unmarshal error reply texts and the reply-less backend stop subscription are unchanged. The backend stop handler takes the decoded backend name, so it can still close that backend's MCP sessions. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(messaging): remove helpers that only tests used BroadcastRoots, ControlRoots and SubjectRoot had no production caller. The roots spec now asserts every served root through ValidateSubject instead. MatchSubject moves back into the test support package, the only place that used it, with its table. NATSAgentRPCServer drops the subscription list it stored and never read, and NewNATSAgentRPCServer gets a doc comment. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(mcp): round trip the agent RPC server over a real NATS server One spec sends a tool request and a discovery request through NATSAgentControl to NATSAgentRPCServer and checks that the handlers see the decoded requests and the replies come back. It also puts an undecodable body on the tool subject and checks the server answers with an unmarshal error instead of leaving the requester to time out. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: describe the distributed transport seams The developer note now lists the final seams: fan-out, queues, both halves of the control verbs and of agent RPC, and the dial. It records the open items a second carrier has to handle. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test: pin the in-flight limit each queue consumer asks for The work queue specs pin what Consume does for a given limit, but nothing pinned which limit each production consumer passes. Changing the agent worker's MCP CI limit from 1 to 0 would have let MCP CI jobs run concurrently on each worker with every test green. Move the MCP CI Consume call into startMCPCIConsumer with the same wiring and pin that it asks for (WorkMCPCI, 1). Pin that NATSDispatcher.Start asks for (WorkAgentRun, maxConcurrent) for several limits. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: remove helpers the branch left without a caller SubjectJobCancelWildcard lost its last subscriber when the frontend stopped listening on jobs.*.cancel; the NATS permissions and conformance suite spell the subject out, so nothing reads the constant. decodeBackendStopRequest returned a stopAll flag that production dropped and only a test read. decodeBackendStop is now the single decoder with the same semantics: an empty body is stop-all, an empty Backend is stop-all, malformed JSON is an error. stopBackends still derives stop-all from Backend, so no reply changes. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(messaging): keep an explicitly empty agent queue a plain subscription Before the work queue seam the agent worker passed LOCALAI_AGENT_QUEUE straight to QueueSubscribe, so an explicitly empty value made a plain subscription and every agent worker ran every agent run. WithAgentRunRoute replaced an empty queue with agent-workers, which silently changed that. Keep the queue as given once the option is applied. An empty subject still falls back to agent.execute, since it never had a meaning of its own. The flag default stays agent-workers, so only an explicitly empty value reaches this. Assisted-by: Claude:claude-sonnet-5-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: correct comments and record the PR B notes Fix the recordingFactory comment (it also records the parallel flag), document that a negative maxInFlight is unbounded and that Unsubscribe from a handler deadlocks, and say a permanently undecodable payload returns nil. Record controlHandler's undecodable return as a kept exception, and add the second carrier notes to the developer note: the reconciler has no ClientFactory option, the logs proxy honours HTTP_PROXY, verbs one carrier serves need an opt-out, terminal replies come from the result event, and agent runs publish through the NATS-bound EventBridge, which is not an additive change. 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> |
||
|
mudler-agentandEttore Di Giacinto
|
97ad8f1d70 |
fix(distributed): stage the files a model install declares (#12309)
* fix(distributed): stage every shard of a split GGUF A split GGUF is configured by its first shard only. llama.cpp opens the other "-0000N-of-0000M.gguf" files from the same directory by name. The router staged only the configured path, so the worker received shard 1 and the load failed with "failed to load GGUF split". The router now stages the remaining shards next to the first one. A missing shard fails the load and names the file. The file count for progress and the payload size also include all shards. The payload size feeds the load deadline and the disk-headroom check. For a 111 GB model whose first shard is 10 MB, both were sized for less than 1 GB. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): stage the files a model install declares Replace the split GGUF file name matching with the model's own file list. A gallery install or an import records every file of the model in ._gallery_<name>.yaml (files:), and a config can list more under download_files:. The router now stages all of these files, not only the files that the config's path fields name. This includes the other shards of a split GGUF, which llama.cpp opens by name. The application gives the router a resolver that reads the two lists. The resolver looks up the files by model name when it stages them, so a replica that the reconciler loads from saved load options gets the same files. backend.proto does not change. A declared file that is missing on the frontend is skipped with a warning. The load deadline and the disk headroom check include the declared files. Assisted-by: Claude:claude-opus-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
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> |
||
|
Adira Denis Muhando
|
869000ceb7 |
fix(distributed): exclude pinned models from cluster eviction and idle scale-down
pinned: true was only honoured by the per-node watchdog. Every distributed eviction path was pinned-blind: the router's LRU eviction (EvictLRU, evictLRUAndFreeNode) and the replica reconciler's idle scale-down would happily unload a pinned model — and since eviction is gated on in_flight = 0, a pinned model became eviction-eligible the instant each response completed. Under capacity pressure that surfaces as the backend being freed immediately after every request (#11101). Wire the model config loader into the router and reconciler through a new PinnedModelResolver seam (mirroring ConcurrencyConflictResolver): - EvictLRU passes the pinned set into FindLRUModel's query so the next-oldest unpinned model is selected instead of the attempt failing - evictLRUAndFreeNode filters pinned models inside its locked selection - scaleDownIdle skips pinned models entirely: trimming to the floor still means requests beyond the survivor's capacity pay a cold reload Deliberate teardown (admin unload, model delete, node drain) intentionally still applies to pinned models, as does dead-row reaping (state correction, not eviction). Regression specs verified to fail with the exclusion disabled. Addresses the cluster-side eviction gap in #11101 Assisted-by: Claude Code:claude-fable-5 [Claude Code] Signed-off-by: Adira Denis Muhando <dennisadira@gmail.com> |
||
|
Ettore Di Giacinto
|
a9f8062dd5 |
feat(nodes): add pluggable routing pipeline
Route prefix-cache replica selection through composable filters, weighted scorers, and a replaceable picker. Preserve the existing load guard and deterministic selection policy while exposing per-model scorer weights through scheduling configuration. Assisted-by: Codex:gpt-5 [go-vet] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
aff9db9758 |
fix(distributed): resolve paths for virtual models (#11911)
Virtual model names have no primary file to anchor the worker path. Companion assets still stage successfully, but relative options retain an incorrect model directory and fail to load. Derive the worker root from successfully staged option assets when the primary path is absent. Cover Buffalo packs, files, directories, overrides, and failed transfers. Document the frontend upgrade. Assisted-by: Codex:gpt-6 golangci-lint Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
9afe10ba21 |
fix(distributed): survive a slow control-plane database (#11837)
* fix(distributed): evict only when a node is known to be full scheduleNewModel asked the registry for a free replica slot and treated every error as "this node is full", so a control-plane database slow enough to time out the lookup evicted a healthy loaded model. The evicted process died, a peer frontend still holding its address dialled the dead port and retried, and the model thrashed between nodes. The comment on the branch already said it meant a full node; the code never tested for it. Evict only on ErrNoFreeSlot. Any other error now returns and names the lookup that failed, so a slow database degrades into a diagnosable load failure instead of into lost work. An audit of the rest of the router found one branch of the same shape: node selection discarded the error from its last-resort finder, so a database timeout there also produced a nil node and evicted for it. That path now returns unless the finder said gorm.ErrRecordNotFound, which is the only answer that means the cluster had no node to give. No other destructive branch in router.go fires on a generic error. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): checkpoint heartbeat writes instead of writing every beat Every heartbeat UPDATEd backend_nodes. Six nodes at a ten second beat is roughly 52,000 writes a day against a six-row table, and that churn is what turned a blocked autovacuum into a 460 MB table whose six-row scan cost 867 ms and timed out the queries that place models. A beat carrying only a fresher timestamp now waits for the checkpoint interval. Each reported field is compared against the value last persisted rather than tested for presence, because a worker sends its disk figures on every beat and presence alone would suppress nothing. A node's first beat, a changed total VRAM, total disk or GPU vendor, and a free VRAM, RAM or disk reading that has moved more than 256 MiB from the persisted value all still write at once. A node that is not active is never suppressed, because it recovers only when the health monitor sees a fresh timestamp. The persisted column is up to one interval stale by design, so the stale-node threshold moves from 60s to 5m to cover it. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): fail worker readiness when a held backend is unreachable The readiness gate tracked only the NATS link, so a worker whose backend processes had died still answered /readyz with 200 and kept receiving loads. One node did exactly that during an incident: it reported healthy while its backend port refused connections, and every load routed to it failed. Readiness is now the NATS link and, for each backend process the worker believes it is running, a short dial of its recorded address. A worker holding no backends stays ready, because idle is a healthy state. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): keep a starting backend out of the readiness dial set A backend process is inserted into the supervisor map with its gRPC address already recorded, but the address refuses connections until the gRPC server binds, which the startup poll allows up to 30 seconds for and which takes 10 to 15 seconds on a slow node. The new data-path readiness probe dialled that address straight away, so a worker answered /readyz with 503 for the whole of every cold backend start. The container HEALTHCHECK absorbs that, but a Kubernetes readinessProbe at 10s does not, and the worker would leave rotation each time it loaded a model. The skip for a stopping process had no counterpart at the other end of the lifecycle. Backend processes now carry a serving flag, set where the startup health-check gate succeeds, and the probe dials only processes that are serving and not yet stopping. backendStartStillValid becomes markBackendServing: the check and the mark must share one lock hold, so the flag can only ever land on the entry the key currently owns. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): export control-plane database health gauges Four transactions wedged on a corrupt index held the vacuum horizon open for 42 days. Nothing measured it, so the first symptom anyone saw was models failing to load six weeks later, by which time a six-row table had grown to 460 MB. Export the oldest xmin age, the longest open transaction, and the dead tuple ratio on the registry tables. The first is the number that would have caught it: it sits near zero in health and was 21,002,291. Sampling is scrape-driven behind a cache, and a failed sample reports the last good values rather than failing the scrape, because these gauges matter most when the database is already struggling. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): rate-limit failed control-plane database samples The cache advanced its clock only on a successful sample, so once the database started failing every scrape retried the query immediately. That turned the cache off in the one regime it exists for: a retry storm at scrape cadence aimed at a database already in trouble. A catalog read that consistently exceeds the 5 second timeout also paid that cost on every scrape, with all scrapes serialised behind the sampler mutex. Time every attempt rather than every success, so failures and timeouts cost the same interval as good samples. Whether a good sample exists moves to its own field, keeping the gauges absent until the first success and holding the last good values through later failures. Also note in the runbook that pg_stat_activity cannot see prepared transactions or replication slot xmins, so a healthy-looking xmin age does not by itself rule out a blocked horizon. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): pin that a failing database evicts nothing Exercises the real distributed stack against a control-plane database that refuses the router's slot lookup, and asserts the scheduler reports the lookup it could not answer instead of falling through to eviction. The failure is injected with privileges rather than a statement timeout. A timeout set with ALTER DATABASE also breaks AutoMigrate, and it leaks into every later spec in the suite unless it is reset, so the spec would end up testing the migration rather than the scheduler. Instead the spec creates a dedicated login role, points a second gorm handle at it, and revokes that role's SELECT on node_models.replica_index. This has to be a separate role: the test container's owner is a PostgreSQL superuser, and superusers bypass every privilege check, so revoking from CURRENT_USER is recorded and then ignored. The revoke is scoped to one column on purpose. Revoking the whole table would also blind node selection, which runs first and has a guard of its own, so the scheduler would never reach the slot lookup this spec is about. Leaving every other column readable lets selection succeed and lands the refusal exactly on NextFreeReplicaIndex, which plucks replica_index. The grant is restored from BeforeEach via DeferCleanup, so a failing assertion or a panic cannot hand the next spec a role that cannot read. Reverting the eviction guard fails this spec, which is the point of it: the router then reports "no replica slot on keeper and eviction failed" for an error that was never evidence the node was full. The surviving-row assertions are secondary under this injection, because the eviction path reads whole node_models rows and the same revoke blinds it too; a comment in the spec says so, so nobody mistakes them for the load-bearing ones. Also documents why the vector store and the control plane must not share a database: the removable-tuple cutoff is per database, not per table, so one transaction left open anywhere stops autovacuum reclaiming the node registry, and a six-row table bloats into hundreds of megabytes. The note names LOCALAI_AUTH_DATABASE_URL and LOCALAI_AGENT_POOL_DATABASE_URL as the two knobs that must differ, and the localai_control_plane_oldest_xmin_age gauge as the way to see it coming. grep for StaleNodeThreshold and HealthCheckInterval in core/config/runtime_settings_registry.go returns no matches: the distributed duration knobs are not exposed as runtime settings, so the new heartbeat checkpoint interval follows them and needs no registry entry. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): close the review gaps in the heartbeat and health path The stale-node threshold moved from 60 seconds to 5 minutes in this branch because checkpointing makes last_heartbeat up to one checkpoint interval behind by design. Two things were left inconsistent with that. NewHealthMonitor still fell back to a hardcoded 60 seconds when handed a zero threshold, so any future caller that stopped passing the configured value would mark every healthy, beating node offline on every cycle. And the threshold itself had a flag-name constant but no AppOption, no CLI field and no env binding, so an operator who widened --node-heartbeat-checkpoint had no way to widen the threshold to match. The fallback now tracks config.DefaultStaleNodeThreshold, and --stale-node-threshold / LOCALAI_STALE_NODE_THRESHOLD is wired the same way its sibling is. Heartbeat suppression compared the RAW reported free VRAM against the snapshot, but the column persists capAvailable(raw, ceiling). On any node with a VRAM budget set, whose actual free VRAM oscillates above that ceiling, every beat looked material while the persisted value never moved: suppression was defeated on exactly the nodes an operator had configured, and the write amplification this branch exists to remove came straight back there. The comparison and the snapshot now both hold the capped figure, so they measure the same quantity as the column. Fixing that needs the ceiling, and reading it cost a SELECT on every beat, including suppressed ones. The skip decision therefore moved ahead of the updates map and now reuses the ceiling cached on the last durable write, while the write path still re-reads it before capping anything. A ceiling that changed inside the checkpoint window can cost one extra or one late write; it cannot persist a wrong figure. A suppressed beat now costs no query at all. Also: the operations section now says to grant pg_read_all_stats to the LocalAI role, because PostgreSQL blanks backend_xmin and xact_start for sessions owned by other roles, and the transaction that wedged the horizon in the incident was a co-located vector store connecting as a different role, so without the grant the new gauge sees only our own sessions. The compose healthcheck comment now describes readiness covering the backend data path, and the control-plane gauge registration records the otel.SetMeterProvider ordering it depends on. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): resolve the gauge's table names through gorm The dead-tuple gauge queried pg_stat_user_tables against a hardcoded list of three table names. Those three do not agree on where their name comes from: BackendNode and NodeModel take gorm's default pluralisation, while GalleryOperationRecord overrides TableName, and gallery_operations already had a constant of its own that the list duplicated. A literal list keeps compiling after any of that moves, and the query then matches nothing. The failure is silent and it points the wrong way: a dead-tuple ratio that matched no rows reports the same numbers as a cluster with no bloat, so the gauge would look healthiest exactly when it had stopped working. Ask gorm what each model is stored as instead, which follows a TableName override and the default pluralisation alike. A spec pins that the override really is consulted: naive pluralisation of the type would give gallery_operation_records, so the resolution cannot quietly stop asking the model. 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 GiacintoandClaude Opus 5
|
5555a3c569 |
fix(nodes): skip checksum sidecars when staging option dirs
stageDirectory and countStageableFiles already skip them, but stageOptionDir did not - and it is the path sherpa-onnx voices take for espeak-ng-data. The receiver writes "<file>.sha256" for every file it accepts, so staging the sidecars made it write sidecars for those in turn, one level deeper on every load. Observed on a live node: "<file>.sha256" repeated eleven times, 5077 junk files out of 7832 in the models dir, and still growing. Staging never finished, so vits-piper-it_IT-paola-sherpa stayed permanently "staging on node" and every realtime warmup needing that voice failed with the session then going silent. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0142UfUh8HWxdim5JZqf8Tr6 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
80e3240f2d |
feat(distributed): key scheduling rules by a model alias (#11771)
Node placement and replica rules could only name a model, so an operator who pinned "llama3" to the GPU tier had to rewrite the rule whenever a different model took over that job. An alias already gives a stable name for whichever model serves it, and a rule on that name makes it a deployment slot: repoint the alias and the placement follows. A rule keeps the name the operator chose. Reads resolve that name through the config loader to the model the rule governs, so the reconciler counts, schedules and trims replicas of the target, and the router finds an alias-keyed rule from the target it is already routing. An alias that resolves to nothing governs nothing loadable, so the reconciler skips it and the write paths refuse it. A replica is shared by every name that resolves to it, so only one rule can decide where it runs. The REST and MCP write paths reject a rule whose target another rule already governs. A pair that arrives some other way, such as a seed file or an alias repointed onto a model that already has a rule, resolves in favour of the rule named after the model itself and then the oldest, and the rest are listed as shadowed. The eviction guard is the exception: it matches rules to replicas in raw SQL inside a locking transaction and cannot resolve an alias. It reads a stored target that the reconciler refreshes each tick, and falls back to the rule's own name when that target is empty. Assisted-by: Claude:claude-opus-5 golangci-lint eslint Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
2c68fa1eb6 |
fix(distributed): keep eviction inside the model's node selector
When no node the selector allows has a free slot, scheduling falls back to evicting the least-recently-used idle model. That eviction searched every healthy node, so it freed a slot on a node the selector forbids and the model was then placed there: pinned to one class of hardware and running on another. An unrelated model pays for it. On this cluster an embedding model pinned to Apple hardware could not reach its only matching node, so each attempt evicted a large language model from an Nvidia node, failed to start there anyway, and left the evicted model to reload. Repeated, that reads as one replica bouncing between nodes. Eviction is now restricted to the candidate set the selector produced. With no selector the candidate set is nil and eviction stays global. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [golangci-lint] |
||
|
Ettore Di Giacinto
|
c541dbeef4 |
fix(distributed): check a node answers before scheduling onto it
A node's status comes from its HTTP heartbeat. Backend installs travel over NATS. The two are independent, so a worker that dies stops answering on the bus at once but stays healthy in the database until its heartbeat ages out. Inside that window the scheduler picked a node it could not reach, and the request failed with "no responders available" rather than moving to a node that was up. The scheduler now probes the node it selected and, when nothing answers, marks it unhealthy and selects again. The demotion is what makes the retry terminate: the next selection reads only healthy nodes. It also tells the other frontends what this one learned, so the cluster does not rediscover a dead worker one failed request at a time. Only nats.ErrNoResponders counts as absent. A worker that answers slowly stays eligible, because dropping it would cost capacity that is really there. The probe reuses the models.running subject: a new subject would go unanswered by workers that have not been upgraded, and every one of them would then look dead. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-5 [golangci-lint] |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
82c191afad |
fix(distributed): keep model replicas config-consistent (#11664)
* docs: design configurable copy buffering Document the context-aware copy buffer option and its validation plan. Assisted-by: Codex:gpt-5 * docs: design durable distributed staging operations Assisted-by: Codex:gpt-5 * docs: design distributed model config revisions Assisted-by: Codex:GPT-5 [apply_patch] [exec_command] * feat(config): add stable model revisions Hash typed model configuration and effective protobuf options deterministically for distributed revision comparisons. Assisted-by: Codex:GPT-5 [apply_patch] [exec_command] * feat(worker): acknowledge exact model stops Assisted-by: Codex:GPT-5 [apply_patch] [exec_command] * feat(nodes): track model config revisions Assisted-by: Codex:GPT-5 [apply_patch] * fix(distributed): retry quarantined model cleanup Stop quarantined replicas by exact process identity, retain failed cleanup as durable capped retries, and compare-and-delete only the claimed registry row. Process one sufficiently leased row at a time so multiple frontends cannot duplicate slow cleanup work. Assisted-by: Codex:gpt-5 * fix(distributed): bind loads to config revisions Assisted-by: Codex: GPT-5 [OpenAI Codex] * fix(modeladmin): apply config revisions consistently Route model edits, patches, state changes, deletion, and peer refreshes through the same revision lifecycle. Quarantine stale replicas before exact cleanup and report durable pending cleanup without failing successful config writes. Assisted-by: Codex: GPT-5 [OpenAI Codex] * feat(distributed): expose model config revision state Document replica revision observability and durable cleanup behavior. Keep pending cleanup explicit in model mutation responses and verify endpoint contracts expose revision state without serialized load options. Assisted-by: Codex:GPT-5 [OpenAI Codex] * test(distributed): cover model revision convergence Exercise cross-frontend quarantine, stale replay rejection, exact cleanup retry, worker re-registration, and current-generation replica convergence against the distributed PostgreSQL harness. Assisted-by: Codex:gpt-5 * fix(distributed): pass config revision CI checks Keep configured gallery sources out of authoritative runtime snapshots only after validating their real schema, and harden rollback snapshots against symlink races and non-regular files. Assisted-by: Codex: GPT-5 [OpenAI Codex] --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
88edd7fc7f |
fix(distributed): run cold model loads as durable jobs instead of holding the advisory lock (#11514)
* fix(advisorylock): set statement_timeout alongside lock_timeout
WithLockCtx already overrides a deployment-wide lock_timeout on its
dedicated connection so a blocking pg_advisory_lock() waits its turn
instead of failing with 55P03. statement_timeout aborts that exact same
statement independently, with SQLSTATE 57014, and was not overridden.
Production roles commonly carry statement_timeout=60s. Any guarded
section longer than that (a cold model load stages for tens of minutes)
therefore killed every concurrent waiter:
advisorylock: acquiring lock 9003261067483446873: ERROR: canceling
statement due to statement timeout (SQLSTATE 57014)
Derive it from the same context budget as lock_timeout, with a matching
RESET so the pooled connection is returned clean.
Assisted-by: Claude Opus 5 [claude-code]
* feat(distributed): add ModelLoadJob, the durable cold-load record
A cold load in distributed mode is a long-running background job, but it
was modelled as a synchronous side effect of an inference request: the
whole of it (backend install, multi-GB staging, checkpoint load) ran
inside the per-model advisory lock. Loading a 35.7 GB GGUF held that lock
for ~20 minutes, so every concurrent request for the same model blocked
on pg_advisory_lock and died at the role's 60s statement_timeout.
Introduce the row that lets the lock shrink to a decision. Exactly one
ModelLoadJob may be active per tracking key; that uniqueness — not the
lifetime of a lock — is what de-duplicates concurrent loaders across
replicas. ClaimLoadJob does its read-then-write under the advisory lock
and nothing else: no network, file or gRPC I/O inside the guarded
section, so a claim costs milliseconds no matter how long the resulting
load takes.
LastProgress is a heartbeat rather than a byte counter. A checkpoint load
legitimately moves zero bytes for many minutes, so a reaper keyed on byte
movement would reclaim a healthy job mid-load; byte progress stays the
concern of load_deadline.go. A job whose heartbeat stops for longer than
the orphan window is reclaimable, so a replica killed mid-load cannot
wedge a model permanently.
Failed jobs keep their row for a short grace so an immediately-following
request reports the real cause instead of silently starting a fresh load
of a model that just failed.
No caller yet — the router moves onto this in the next commit.
Assisted-by: Claude Opus 5 [claude-code]
* refactor(distributed): run cold loads as jobs, outside the advisory lock
Route wrapped the entire cold load — node selection, backend install,
multi-GB staging and the remote LoadModel — in the per-model advisory
lock. The lock's job is to de-duplicate concurrent loaders, a decision
that takes milliseconds; holding it for the tens of minutes the resulting
work takes is what turned a dedup mechanism into a cluster-wide outage
for that model.
Split it into a claim and a run. The claim is the only thing left inside
the lock. The run is a background job owned by the claiming replica and
bounded by the same progress-extended deadline as before; every other
request for that model — local or on another replica — attaches as a
waiter and is served the moment the model is ready, with no duplicate
load and no lock contention.
Waiters share one broadcast rather than an ordered queue: they all want
the identical outcome, so ordering them would add fairness machinery that
changes no result. The local channel wakes same-replica waiters instantly
and a 2s DB poll is the authority, because a waiter on another replica
has no channel to close. On wake a waiter re-runs the warm path rather
than trusting the signal — the model may have been evicted in between.
A waiter whose client disconnects returns immediately and the job keeps
running; it belongs to the job record, not to the request. A failure is
recorded on the row so every waiter reports the real cause, and the row
survives briefly so the next request does not read "no job" as "not
loading" and start a duplicate load of a model that just failed.
The runner heartbeats the row on a fixed interval whether or not bytes
are moving, which is what keeps a legitimately silent checkpoint load
from being reclaimed as an orphan. Phase (installing/staging/loading) and
placement ride to the heartbeat on the context, the same seam
load_deadline.go already uses, so single-host paths are untouched.
Non-distributed mode (no DB) keeps the inline load exactly as it was.
Assisted-by: Claude Opus 5 [claude-code]
* feat(distributed): bound the wait for a loading model and answer with progress
A request whose model is cold-loading now attaches to the running job and
is served the moment the model is ready. That wait has to be bounded: a
held HTTP request cannot survive real infrastructure, and an ingress or LB
idle timeout kills a twenty-minute request regardless of what LocalAI
does.
New LOCALAI_MODEL_LOAD_WAIT (default 60s) bounds the CALLER, never the
load — the job keeps running either way. On expiry the request gets 503
with Retry-After and a structured body naming the model, the node, the
phase, byte progress and an ETA. The `error` envelope keeps OpenAI
clients working; `loading` is additive so they ignore it.
The ETA comes from the job's own observed rate and is omitted rather than
guessed until enough bytes have moved for that rate to mean anything: a
confidently wrong ETA on a twenty-minute wait is worse than none.
Retry-After is that ETA when known, clamped to [5s, 300s], and the wait
budget otherwise.
LOCALAI_MODEL_LOAD_WAIT=0 waits unbounded, for deployments with no proxy
in front. Zero in the config struct still means "unset, use the default",
so the CLI records the operator's zero as ModelLoadWaitUnbounded rather
than losing the distinction.
The distributed branch of ModelLoader.loadModel wrapped the router's
error with %s, which flattened it to a string. Use %w: the typed error is
what the HTTP layer keys the 503 off.
Assisted-by: Claude Opus 5 [claude-code]
* feat(api): add GET /api/models/{id}/load-status
A client that receives 503 while a model stages onto a worker needs
somewhere to poll. This returns the same `loading` object the 503 carries
— phase, node, byte progress and ETA — or 404 when no load is running.
Read-only and observability-shaped, so it is deliberately neither
admin-gated nor feature-gated: it explains a 503 the caller just
received, and hiding that behind a per-modality feature would make the
explanation for a failed image request depend on chat permissions. It
also gets no MCP tool, since there is nothing here an admin would manage
conversationally.
Registered on the surfaces from .agents/api-endpoints-and-auth.md: the
swagger block (existing `models` tag, so /api/instructions needs no new
area), the endpoint discovery maps in RegisterLocalAIRoutes, regenerated
swagger, and the distributed-mode docs page. No FLAG_* usecase is
involved, so capabilities.js is unchanged.
Assisted-by: Claude Opus 5 [claude-code]
* feat(ui): show cold-load progress in Chat and retry when the model is ready
A chat request for a model that is still staging onto a worker now gets a
503 carrying live progress instead of an error. Render it: the composer
shows the phase (installing / staging / loading), the node, the percent
and the ETA, then polls load-status and re-sends the request the moment
the model is ready.
Reuses the staging progress idiom the page already had rather than
inventing a second one — the two sources are folded into one
loadProgress, with the load job winning because it is authoritative
across frontend replicas and knows the phase, where the staging operation
only knows about a byte transfer this replica happens to be performing.
Waiting is bounded (three send attempts, ~30 min of polling each), so a
load that never finishes still surfaces as an error rather than as a
spinner nobody questions. An aborted generation stops the polling too.
Assisted-by: Claude Opus 5 [claude-code]
* fix(distributed): check warm-path cleanup errors
The router moved legacy cleanup calls onto newly linted lines. Report
cleanup failures while preserving the fallback to a cold load.
Assisted-by: Codex:gpt-5 [golangci-lint]
---------
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
878a0d00a1 |
fix(distributed): reaper reaps live backends, ghost model stubs, in_flight leak, sidecar staging runaway (#11142)
* fix(distributed): stop the probe reaper from orphaning busy backends
The reconciler's liveness probe is a 1s gRPC HealthCheck, and a single
failed probe deleted the model's node_models row. A backend that is
merely busy cannot answer it: single-threaded Python backends (video and
avatar generation) block for minutes inside one request, so the reaper
was deleting registry rows for backends that were alive and mid-request.
The model then vanished from the nodes page while it was still
generating, and because the row was gone the in-flight decrement had
nothing to decrement ("DecrementInFlight: no matching row or already
zero"). Every subsequent request re-routed and re-staged the full model
from scratch.
Two guards:
- Replicas with in-flight requests are excluded in SQL. A row that is
actively serving is proof of life, and the running request is
exactly what stops the backend from answering the probe.
- Idle replicas must miss three CONSECUTIVE probes before removal, so
a transient blip cannot orphan a live replica. A successful probe
resets the streak.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
* fix(distributed): drop the local model stub when its last replica goes
In distributed mode every routed model leaves an in-process stub in the
frontend's ModelLoader, and DistributedModelStore.Range reports local
stubs UNION the registry rows. Every registry removal path deletes only
the DB row, so the stub outlived the replica and the model was reported
as loaded forever.
That is the "loaded on the home page, absent from every node" ghost:
/system reads the union and still sees the stub, while /api/nodes/models
reads the registry and correctly sees nothing. It never self-healed,
and both frontend replicas showed it independently.
The replica-removed chokepoint could not fix this as it stood, because
it held a SINGLE hook that the prefix cache already owned, and it was
registered only when the prefix cache was enabled. Registering a second
listener would have silently displaced the first.
- Turn replicaRemovedHook into a list (AddReplicaRemovedHook), so
independent subsystems can each register without displacing others.
- Add NewLocalStubInvalidator, which drops the local stub once no
healthy replica of the model remains anywhere in the cluster, and
wire it unconditionally in startup.
The stub is kept while another node still serves the model: the
frontend is right to consider it loaded, and each request re-routes
through SmartRouter to pick a live replica anyway.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
* fix(distributed): stop staging checksum sidecars back to workers
The file transfer server writes a "<file>.sha256" sidecar next to every
file it accepts. The sender walked the model directory with no filter,
so it staged those sidecars too, and the receiver duly wrote a sidecar
for each sidecar. Every staging pass multiplied the tree:
config.json -> config.json.sha256 -> config.json.sha256.sha256 -> ...
One LongCat snapshot had grown to 498 files, 466 of them chained, up to
29 levels deep, and the staged file count climbed on every pass. This
inflates each transfer and grows disk without bound on both ends.
Skip hash sidecars in stageDirectory, and mirror the skip in
countStageableFiles so the progress bar still reaches 100%. The check is
"a sidecar sitting next to a real file" rather than a blanket suffix
ban, so a model that genuinely ships a .sha256 payload with no
corresponding base file is still transferred.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
* fix(distributed): classify the liveness probe instead of gating on in_flight
The previous commit excluded replicas with in-flight requests from the probe
reaper. That was the wrong guard, and could invert the bug it fixed.
in_flight has no decrement guarantee: track() balances its increment with a
defer, but a frontend killed mid-request never runs it, and the load-time
reservation is released only when the first inference completes. Nothing
resets a leaked counter. Gating the reaper on it therefore meant a leaked
counter would shield a genuinely dead replica from ever being reaped.
Nor was patience alone a fix: three misses at the default interval is ~90s of
silence, while the generation that triggered this blocks for 15+ minutes.
The real conflation was in the probe itself. A gRPC HealthCheck against the
backend's serving port measures "is it idle enough to answer", not "does the
process exist", and probeLoadedModels discarded the error that tells them
apart. Because the gRPC client is lazy, the status code is decisive:
- DeadlineExceeded: transport fine, nothing serviced the RPC. Busy.
- Unavailable: nothing is listening. Gone.
ModelProber now returns a ProbeOutcome, and only ProbeUnreachable counts
toward the reap threshold. ProbeBusy clears the streak: it is evidence of
life. A blackholed network reads as busy too, deliberately, since whole-node
failure is the health monitor's job.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
* feat(distributed): reconcile replicas against worker-reported processes
Probing a backend's own serving port cannot distinguish "busy" from "gone"
without inferring it from an error code. The worker can answer directly: it
spawned the process, holds the handle, and its reply is not blocked by
whatever that backend is doing.
Adds a models.running request-reply subject. The worker answers out of its
in-memory process table, reporting each live process as (modelID,
replicaIndex, address) — the supervisor's process keys are `modelID#replica`,
which is isomorphic to a NodeModel row, so the reconciler can diff the two
directly.
reconcileNodeProcesses runs before the port probe and reaps rows for models
the worker is not running. Models the worker vouches for get updated_at
bumped, which takes them out of the port prober's stale set entirely: that is
what keeps a backend deep in a long generation away from the probe in the
first place, rather than relying on classifying its silence after the fact.
A worker that does not answer is skipped, not assumed empty. A messaging
failure says nothing about the processes, and assuming the worst would delete
a node's rows on a transient NATS blip; the port probe stays as the fallback
for those nodes. Rows younger than probeStaleAfter are ignored so a freshly
created row is never judged against a process table that has not caught up.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
* fix(distributed): stop in_flight leaking and pin replicas against eviction
A leaked in_flight counter is not cosmetic. FindLRUModel,
FindGlobalLRUModelWithZeroInFlight and the router's eviction query all require
in_flight = 0, so a replica whose counter never came back is pinned and its
VRAM is unreclaimable for the lifetime of the process.
Two halves.
The source: routing reserves in_flight = 1 at load time so a freshly loaded
replica is not evicted out from under the request that caused the load. That
reservation was released ONLY by the first inference completing, so a route
torn down before any inference ran (client disconnect, handler error, failure
between load and the backend call) stranded it. newRouteResult now wires the
reservation to a sync.Once fired by whichever comes first, the first inference
or route teardown, and replaces three copies of the old wiring.
The backstop: a sweeper for counters leaked by paths that cannot run a defer
at all, such as a frontend killed mid-request.
Identifying a leak by elapsed time alone is unsafe. IncrementInFlight stamps
last_used at request START and nothing moves it while the request runs, so a
long generation is indistinguishable from a leak by age, and resetting there
would expose a serving model to eviction. The probe supplies the missing bit:
a backend that answers a health check promptly is not inside a request,
because that is precisely what a busy one cannot do. Requiring the row to also
be idle for 30 minutes covers backends that serve in parallel and can answer
while working, since those keep last_used fresh through each new increment.
Two existing tests asserted the old behaviour ("No decrement on Release").
That assertion was the leak, so both now pin the release instead.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5 [Claude Code]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
|
5d57c08c6e |
feat(distributed): cache staged-artifact hashes and publish the model load lifecycle (#11121)
feat(distributed): cache staged-artifact hashes and publish load lifecycle Every load request re-hashed every staged artifact on the controller (probeExisting and the upload path both re-read the full file), which for a large multi-file model on NAS-backed storage is minutes of pure re-reading per request even when nothing changed - observed as ~9 minutes of "Upload skipped (file already exists with matching hash)" before every avatar generation. Cache the local hash in the same .sha256 sidecar the worker-side transfer server already maintains, invalidated whenever the sidecar is older than the file. The whole staging+loading phase was also invisible: the NodeModel row was only written after LoadModel succeeded, so /api/nodes and the UI showed nothing while a cold load spent 10+ minutes staging - indistinguishable from nothing happening. Publish the lifecycle instead: "staging" as soon as the node is chosen, "loading" when the checkpoint load starts, and the existing "loaded" on success, with the row removed on any failure so a dead load does not leave a phantom replica. The early row also reserves the replica slot against concurrent schedulers. The nodes view already renders non-loaded states on model chips; style "staging" like "loading". Audited every state-filtered registry/router query: eviction, routing, reconciler and idle-model queries all filter state='loaded' explicitly, so the new transitional rows are visible to observability surfaces but inert to scheduling decisions (except slot occupancy, intentionally). Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
6584db992f |
fix(nodes): never schedule a model onto a node that cannot store it (#11054)
* fix(nodes): never schedule a model onto a node that cannot store it
A worker whose models filesystem was 100% full kept advertising
`status: healthy`, stayed a scheduling candidate, was picked to host a
70 GB video model, accepted the staging request, transferred ~17 GB and
only then failed:
staging .../whisper-large-v3/model.fp32-00001-of-00002.safetensors:
upload to node b7bacbf4-... failed with status 500:
writing file: /models/longcat-video-avatar-1.5/...: no space left on device
The node was at 937G/937G/0-avail. Total elapsed before the truth
surfaced: 16 minutes, for a decision that could never have succeeded.
The worker health signal only ever proved liveness. `/readyz`
(WorkerReadiness/NATSReadiness) checks the NATS link; `status: healthy`
in the registry is driven by heartbeat recency. Node capacity carried
VRAM and RAM but no disk figure at all, and the router compared model
size against VRAM only — nothing anywhere looked at free space on the
filesystem that staging actually writes to.
Report it, then use it:
- Workers now measure the filesystem backing their MODELS directory
(not `/` -- staged weights land in the models path, and that mount is
very often separate) and report `total_disk`/`available_disk` on
registration and on every heartbeat. Free disk moves faster than VRAM
under staging traffic, so the per-heartbeat refresh matters.
- The SmartRouter drops nodes that cannot store the model before it
picks one. The requirement comes from `modelPayloadBytes` -- the same
local paths `stageModelFiles` uploads, already computed for the
size-derived load budget -- plus a 5% / 1 GiB margin, rather than a
fixed percentage of the node's disk. A percentage threshold would take
a small-but-usable node out of rotation for models it could hold, and
on a homogeneous cluster would strand every node at once.
- When no node fits, scheduling fails immediately with an error naming
the requirement and each node's free space, instead of picking one and
discovering it mid-transfer.
Two deliberate non-changes. Low disk does not mark a node `unhealthy`:
the check is per model, so a node too small for one model stays a valid
target for smaller ones. And `total_disk == 0` means "does not report
disk" (pre-upgrade worker, or a failed stat), not "full" -- such nodes
pass through untouched so a rolling upgrade never empties the candidate
pool. A genuinely full node is distinguishable: non-zero total, zero
available. Registry read failures are logged and scheduling continues
unfiltered; a database hiccup must not wedge a cluster.
Free space is surfaced on the node detail page next to VRAM, since the
incident's signature was a node that looked entirely healthy.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
* feat(nodes): make the disk-headroom check operator-controllable
The admission check added in the previous commit had no off switch. A
scheduler-side veto with no escape hatch is a liability: our size
estimate can be wrong (deduplicating or compressing filesystems, a
backend that fetches its own weights rather than loading the staged
copy), and an operator who hits that has no way out but a downgrade.
Add one knob with two surfaces that share a single source of truth:
- `--distributed-disk-headroom-check` / `LOCALAI_DISTRIBUTED_DISK_HEADROOM_CHECK`
(default true), following the `--distributed-prefix-cache` pattern for
a default-on distributed feature.
- `distributed_disk_headroom_check` in the runtime-settings registry, so
it can be flipped without a restart from `POST /api/settings` and from
Settings -> Distributed in the WebUI.
Both write `DistributedConfig.DiskHeadroomDisabled`, and the SmartRouter
reads that member LIVE on every scheduling decision through a closure
over the application config rather than a value snapshotted at
construction. Env/CLI sets the boot value, the runtime setting overrides
it live, last write wins, and there is exactly one member to read.
Snapshotting would have made the runtime toggle a no-op until restart.
Disabled means WARN, not SKIP. Selection goes back to ignoring free disk
-- byte for byte the pre-check behaviour -- but the check still runs, and
when it would have rejected every node it says so, naming the knob that
suppressed it. Going quiet when switched off would reproduce the exact
condition that made the original incident expensive: a cluster doing
something that could not work and saying nothing. Disabling is also
logged once at startup. Warning only on the total-rejection case keeps
it actionable rather than chatty on a heterogeneous cluster.
Also fixes a false positive in the check itself: shared-models mode
(LOCALAI_DISTRIBUTED_SHARED_MODELS) stages nothing at all -- every node
already mounts this models directory at this path -- so demanding the
full checkpoint size of free space per node would have rejected a
cluster that needs no new bytes. The check is skipped there entirely.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
01fca9c9b2 |
fix(distributed): scale the remote model-load deadline with checkpoint size (#11030)
The gRPC deadline for the remote LoadModel call was a fixed 5m. It starts
only after the backend install and file staging have completed, so it
covers the worker's checkpoint read and pipeline init alone - work whose
duration is proportional to the bytes on disk. A fixed value is therefore
a model-size cliff, not a timeout.
Measured in production: a 70 GB video checkpoint (longcat-video-avatar-1.5)
on an NVIDIA Jetson Thor worker failed reproducibly with
"rpc error: code = DeadlineExceeded" after 953.5s of wall clock. Backend
install plus staging consumed ~11m, then LoadModel got its 5m and expired.
The load never had a chance, and the operator saw only a generic
DeadlineExceeded with no hint that a config value was the cause.
Raising the constant does not fix this. It moves the cliff to the next
larger model - the cluster has to support 600 GB checkpoints - and it makes
a genuinely wedged SMALL model hang for the whole inflated duration before
anyone notices, which is a real regression in failure latency.
So derive the budget from the checkpoint size instead:
budget = 5m + 20s/GiB, capped at 6h
2 GiB -> 5m40s, 70 GiB -> 28m20s, 600 GiB -> 3h25m. The per-GiB rate is
deliberately pessimistic (~54 MB/s of weight read) because the errors are
not symmetric: too long costs only failure latency on a load that was going
to fail anyway, too short is a guaranteed false failure on a healthy load.
The size is measured from the frontend's local model files, over the same
path set stageModelFiles uploads. When those files are not present locally -
a backend handed a bare HuggingFace repo id fetches its own weights on the
worker - there is nothing to measure and the budget stays at today's 5m.
An explicit LOCALAI_NATS_MODEL_LOAD_TIMEOUT still wins outright, in both
directions: a shorter override is honoured, so an operator who wants fast
failure is not silently extended by the heuristic.
The cold-load hold needed widening to match. It extends on staging progress,
but LoadModel reports none, so once the last byte lands the hold expires a
stall window later and would cancel a load still well inside its own budget.
scheduleAndLoad now extends the hold by the load budget plus the staging
margin as it enters the load phase; ModelLoadCeilingFor stays the hold's
starting budget rather than its maximum.
Finally, a deadline that does expire now names the budget, the checkpoint
size it was derived from, and the knob that overrides it, instead of
surfacing a bare "context deadline exceeded".
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
b700a78ae4 |
fix(distributed): make the cold-load hold scale with progress, not wall-clock (#11019)
A 70 GB video checkpoint (longcat-video-avatar-1.5) could not be loaded on a
distributed cluster. The request failed with HTTP 500 after 1499.98s - exactly
the 25m00s cold-load ceiling - while staging was demonstrably healthy: 26 of 57
files and 39 GB transferred at a sustained ~26 MB/s, zero errors, no stalls. It
was not wedged, it was killed by a timer.
ModelLoadCeilingFor covers node selection, backend install, file staging and the
remote LoadModel. Install and load carry their own budgets; staging was covered
only by a FIXED 5-minute margin. But staging time is bytes over bandwidth, not a
constant: 70 GB at 26 MB/s needs ~45m against a 25m ceiling, so the failure is
deterministic for any sufficiently large model rather than a flake. Simply
raising the constant moves the cliff to the next model size - the deployment
target here is checkpoints of 600 GB and beyond.
The ceiling's real purpose is that "a wedged worker can never pin the lock
indefinitely". Progress, not elapsed time, is what distinguishes a wedged worker
from a large one. The hold is now a deadline that extends whenever the transfer
reports bytes and expires a 5-minute stall window after they stop:
- A large model transferring fine continues, for hours if needed.
- A worker that died mid-transfer still fails within the stall window.
Progress is observed at byte level on the transfer itself, via the existing
staging progress callback. Per-file completion would be too coarse - a single
600 GB shard would be indistinguishable from a stall for hours. The observation
point is back-pressured by the socket, so it reflects the network rather than
local disk reads. Observation is coarsened to one timer touch per stall/20 so
the per-read callback stays cheap.
The base budget (unchanged, and still derived from the install and load
timeouts) continues to cover the steps that report no progress, so
LOCALAI_NATS_MODEL_LOAD_TIMEOUT keeps working exactly as before. An absolute
cap of 24h bounds the hold even while progress keeps arriving, so a peer
trickling bytes forever cannot pin the advisory lock; 600 GB at the measured
26 MB/s is ~6.5h, so the cap sits far above any legitimate transfer.
Also fixes the incoherent layering the same error exposed: the resumable upload
carried a 1h retry budget nested inside the 25m ceiling, so the inner budget was
unreachable and the message still blamed it ("failed after 1 attempts within
1h0m0s budget") while the 25m parent was the actual killer. The upload now
adopts the caller's deadline when there is one, and applies its fixed budget
only when nothing above bounded it - which also stops a fixed 1h from
reintroducing the size cliff under the now-extendable parent.
This is the successor to #10968, where a hardcoded 5-minute LoadModel gRPC
timeout was replaced by this derived ceiling. Fixing the inner timeout exposed
the outer ceiling as the new binding constraint.
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
fb4c61d1c9 |
fix(distributed): configurable remote model-load timeout, and reap the load when it times out (#10948)
* fix(distributed): make the remote LoadModel deadline configurable
The router hardcoded a 5 minute gRPC deadline for the remote LoadModel
call. Staging finishes before the timer starts, so those five minutes
cover only the worker backend's own checkpoint load and pipeline init.
A cold load of meituan-longcat/LongCat-Video-Avatar-1.5 (~83 GB) on an
ARM64 Thor worker fails at exactly 302s with DeadlineExceeded while the
backend process is still making progress (CPU time accumulating, RSS
moving as weights are mapped), so the load was cut short rather than
wedged.
Add LOCALAI_NATS_MODEL_LOAD_TIMEOUT / --model-load-timeout mirroring the
existing backend-install timeout knob, defaulting to 5m so unset
clusters keep today's behaviour.
The cold-load hold ceiling (which bounds how long one load may hold the
per-model advisory lock) was derived from the install timeout alone, so
raising the load deadline past it would have been silently clipped.
Derive it from both budgets via ModelLoadCeilingFor:
max(install + load + 5m staging margin, 25m)
With the defaults that is 15m + 5m + 5m = 25m, identical to the previous
constant, and the 25m floor means shrinking either budget can never
tighten the ceiling below what clusters relied on before.
Assisted-by: Claude:claude-opus-4-8 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(distributed): reap the abandoned replica when a remote load times out
The gRPC deadline on the remote LoadModel call only cancels the client
side. A backend blocked in a synchronous weight load never observes its
cancelled handler context, so when scheduleAndLoad gave up it left the
worker loading with nobody waiting for the result.
Observed on an ARM64 Thor worker loading LongCat-Video-Avatar-1.5: the
client returned DeadlineExceeded at 302s, and the backend process was
still alive 30 minutes later having pulled ~57GB from HuggingFace. Every
retry stacked another multi-GB loader on the worker; they had to be
reaped by hand via POST /api/nodes/:id/models/unload.
Send backend.stop for the exact `modelID#replicaIndex` process key we
just abandoned. The exact key matters: a bare model ID stops every
replica on that node, including healthy ones serving traffic.
Only a deadline or cancellation triggers the reap. Any other LoadModel
failure is the backend answering, which means its handler returned and
the process is idle - stopping it there would discard a warm process and
its downloaded weights. The reap is best-effort and never replaces the
load error the caller is waiting on.
The `modelID#replicaIndex` format was already hand-rolled in two places
(the worker's buildProcessKey and pkg/model's log store). Rather than add
a third, export model.BackendProcessKey from pkg/model, the lowest common
dependency of both sides.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 golangci-lint
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
626ae4d51e |
fix(model-artifacts): materialize longcat-video on the controller, and support companion repos (#10949)
* fix(model-artifacts): materialize longcat-video checkpoints on the controller longcat-video loads a checkpoint directory: its backend.py takes request.ModelFile when os.path.isdir(request.ModelFile) and otherwise falls back to snapshot_download. That places it in the same class as transformers/vllm/diffusers/sglang, but the allow-list added in #10910 did not enumerate it, so PrimaryArtifactSpec returned no managed artifact for a bare HuggingFace repo id. The consequence in distributed mode: nothing was acquired on the controller, ModelFileName fell through to the raw repo id, and staging skipped the resulting phantom /models/<owner>/<repo> path. The worker received a blank ModelFile, fell back to request.Model, and downloaded ~83GB from HuggingFace inside the remote LoadModel deadline - so the load could only ever fail with DeadlineExceeded while an abandoned backend process kept downloading. Note this materializes the full repository. The backend restricts its own snapshot_download with allow_patterns, and the avatar repo ships both base_model/ and base_model_int8/ where only one is ever loaded; inferred specs have no way to carry patterns today. Tracked separately. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): warn when staging skips a non-existent model path stageModelFiles logs "Staging model files for remote node" up front, then silently drops any path field that does not exist on the controller. The skip itself is legitimate and must stay: a backend outside managedArtifactBackends that takes a bare HuggingFace repo id gets an optimistically constructed path (ModelFileName falls through to the raw model reference) that was never materialized, and sources its own weights on the worker. Erroring would break those configs. But at debug level the operator is left with a reassuring staging line and no trace of the skip, so a genuine controller-side acquisition gap is indistinguishable from a healthy pass-through - it surfaces much later as a remote LoadModel timeout, on a worker that is quietly downloading tens of gigabytes. Raise the skip to warn and name the field, path, node and tracking key. Behavior is unchanged. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(model-artifacts): allow a config to declare companion artifacts A composed pipeline needs more than one HuggingFace snapshot. LongCat-Video-Avatar-1.5 loads its own transformer but takes the tokenizer, text encoder and VAE from the separate LongCat-Video base repo, so a single-artifact config cannot express it and the backend is left to fetch the second repo itself at load time. Widen the artifact model to target: model plus any number of named target: companion entries. Normalize accepts the new target and constrains a companion name to [a-z0-9][a-z0-9_-]{0,63} because that name is the option key the backend later receives; a companion may not claim primary_file, which only means anything for a load target. ModelConfig.Validate requires exactly one primary and requires it first, since Artifacts[0] is what ModelFileName, size estimation and staging all resolve from. Both acquisition paths now loop instead of touching index 0 alone: preloadOne for an already-installed config, bindPrimaryArtifact for a gallery install. Failure policy differs by provenance. An inferred primary keeps its warn-and-fall-back, because the legacy download path still exists for it. Companions are explicit by construction, so they are all-or-nothing: a config naming one is asserting the backend needs it, and failing at the acquisition boundary is far more legible than a missing-weights error surfacing later inside the backend. The cache key is deliberately unchanged. It hashes source identity only, never name or target, so every already-installed managed model still hits its existing snapshot instead of silently re-downloading. Two specs pin that: one proving a companion and a primary with identical sources agree on the key, and one pinning the digest of a known primary outright. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(model-artifacts): hand resolved companion snapshots to the backend A materialized companion is useless until the backend can find it, and its location is a content-addressed cache key that does not exist until the artifact resolves. A static gallery override cannot carry that, and persisting it into the config YAML would rot the moment a re-resolve produced a new key. Synthesize it instead at load time: each resolved companion becomes "<artifact name>:<snapshot path>" in ModelOptions.Options, reusing the key:value convention backends already parse for options like attention_backend. The value stays relative to the models directory so a remote worker can resolve it under its own ModelPath once staging has rewritten the model root. An option the author set explicitly always wins, so pinning a companion to a local checkout still beats the managed snapshot. longcat-video resolves base_model through ModelPath, the same convention qwen-tts, voxcpm, outetts and ace-step already use for companion assets. Its sibling-directory heuristic is deleted: it looked for a LongCat-Video directory next to the model, which cannot exist under the content addressed .artifacts/huggingface/<key>/snapshot layout, so it was dead code the moment the model became managed. The gallery entry declares both repositories and restricts each with allow_patterns. The avatar repo ships base_model/ and base_model_int8/ and only ever loads one, so fetching the whole repo would roughly double the download. The patterns match the entry's own options (use_distill true, use_int8 default false); enabling use_int8 here also requires adding base_model_int8/**, which is called out in the entry. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): stage managed artifact trees from the models root Staging anchored the worker's models directory on the primary snapshot whenever a model was managed, so a companion snapshot could not reach the worker at all. frontendModelsDir was derived by stripping the Model relative path off the end of ModelFile. For a managed artifact nothing matches: ModelFile is .artifacts/huggingface/<key>/snapshot while Model stays a bare HuggingFace repo id, so the strip was a no-op and the "models directory" came out as the snapshot itself. Two consequences, both silent. Staging keys lost the .artifacts/huggingface/<key>/snapshot prefix, so two snapshots of one model were indistinguishable on the worker. And a companion, which lives in a sibling snapshot directory outside the primary, fell outside that directory entirely: StagingKeyMapper.Key collapsed its files to bare basenames and resolveOptionPath could not resolve the relative option at all, so it was skipped without a word. Derive the models root from the artifact tree instead when the path runs through it, and compute the worker's ModelPath from the file's path relative to that root rather than from the Model field. The legacy layout is unaffected: where Model really is the relative path, the new derivation reduces to the old one, which a regression spec pins. This deliberately changes an invariant that router_dirstage_test.go pinned: for a managed primary, ModelFile and ModelPath were both the snapshot directory, and staging keys were relative to it. Now ModelFile is the snapshot, ModelPath is the models root above it, and keys keep the full relative path. That spec is updated rather than accommodated, with the reasoning recorded inline, because the old invariant is exactly what made a sibling companion unreachable. Assisted-by: 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
8cec22c3b7 |
feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)
* feat(vram): add vrambudget primitive for per-node VRAM caps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply default VRAM budget in xsysinfo aggregate getters Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): wire LOCALAI_VRAM_BUDGET flag to xsysinfo default budget Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): persist VRAM budget via runtime settings with live apply Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(vram): reset process-global VRAM budget after runtime-settings spec Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add VRAM budget field to Settings page Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): store and enforce per-node VRAM budget in the node registry Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply per-node VRAM budget in router hardware defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): report worker VRAM budget in node registration The distributed worker now reports its operator-set VRAM budget string (LOCALAI_VRAM_BUDGET) to the server on registration. The worker keeps reporting RAW total/available VRAM and never sets the xsysinfo process-global budget (that stays standalone-only); the server resolves and enforces the budget uniformly (Task 6). Also closes a Task 6 gap: on re-registration, a struct Updates zero-skips an empty budget, so a worker that dropped LOCALAI_VRAM_BUDGET left the stale cap in place. For non-admin-override nodes the budget columns are now force-written (map Updates) even when empty, so removing the env var clears the cap; admin overrides are preserved unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(vram): drop em dash from worker-clear comment Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget admin endpoints Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget control to the node UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): expose set_node_vram_budget MCP admin tool Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(vram): document LOCALAI_VRAM_BUDGET and node VRAM budget UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): avoid double-applying VRAM budget in GetResourceAggregateInfo The GPU-branch aggregate returned by GetResourceInfo is sourced from GetGPUAggregateInfo, which already caps total/free/used against the process-wide VRAM budget. GetResourceAggregateInfo then applied the budget a second time. For an absolute budget this is idempotent, but for a percentage budget b.Apply resolves the ceiling as a fraction of its input total, so a second pass yields P*(P*T) instead of P*T and distorts UsagePercent (read by the memory reclaimer in pkg/model/watchdog.go). Remove the redundant second application so the budget is applied exactly once, against the raw physical totals, upstream in GetGPUAggregateInfo. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): implement SetNodeVRAMBudget on mcp assistant test stub The LocalAIClient interface gained SetNodeVRAMBudget; the stubClient in core/http/endpoints/mcp used by the assistant tests is a separate implementer and needs the method too (broke golangci-lint typecheck and both test jobs). 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
|
b224c96db6 |
fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)
SetDefaults injected the llama.cpp server options cache_reuse (ApplyServingDefaults) and parallel (ApplyHardwareDefaults, re-applied per selected node by the distributed router) onto every model config regardless of backend. Every other backend ignores options it does not understand, so this was harmless until longcat-video, which strictly validates its options and fails LoadModel with "unknown model option(s): cache_reuse, parallel". Gate both injections behind a new UsesLlamaCppServingOptions allow-list (llama-cpp plus the empty/auto-detect case that resolves to llama.cpp from a GGUF file, mirroring how llamaCppDefaults is registered). This follows the existing UsesLlamaSamplerDefaults precedent for llama-only defaults. The typed NBatch field is deliberately left alone: it is a proto field every backend simply ignores, which is why batch never triggered the error. Also harden the longcat-video backend to warn-and-ignore unknown model options and request params through a testable select_known_options helper, matching the other LocalAI Python backends, so a future server-injected option cannot break loading again. 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> |
||
|
|
29001a88c1 |
fix(distributed): don't let a dead worker pin the model-load advisory lock (#10600)
* fix(distributed): don't let a dead worker pin the model-load advisory lock In distributed mode a chat request could fail with: failed to route model with internal loader: routing model ...: loading model ...: advisorylock: acquiring lock <id>: ERROR: canceling statement due to lock timeout (SQLSTATE 55P03) Root cause is two independent defects in the cross-replica model-load path: 1. SmartRouter.Route holds a per-model PostgreSQL advisory lock for the whole cold-load sequence, which includes installBackendOnNode -> InstallBackend, a NATS request-reply with a 15m deadline (DefaultBackendInstallTimeout) that ignored ctx. When the chosen worker died mid-install, the holder sat on the lock for up to 15m. The detached loadCtx (WithoutCancel) had no deadline, so nothing capped the hold. 2. The acquiring statement, pg_advisory_lock(), is subject to any deployment global lock_timeout. A common operator setting (e.g. 10s) aborts the wait with SQLSTATE 55P03, so every other replica's request for that model hard -errored instead of waiting for the in-progress load and reusing it. For the ~15m window the model was effectively unroutable. Fixes: - advisorylock.WithLockCtx (postgres): SET lock_timeout = 0 on its dedicated connection (RESET before it returns to the pool) so the Go context, not a deployment-wide GUC, governs how long we wait. Waiters now block and then re-check, reusing the model another replica just loaded. - SmartRouter: bound the detached loadCtx with a single ModelLoadCeiling so the lock is always released in bounded time even if a sub-step wedges. Default is the configured backend.install deadline + 10m (staging + LoadModel margin), so a legitimately slow load is never cut. - installBackendOnNode: use singleflight.DoChan + select on ctx.Done() so the install wait honors cancellation; the ceiling can then actually free a caller pinned behind a dead worker. The shared install still coalesces via singleflight. Reproduced both defects as failing tests first (a real 55P03 against a testcontainer with a short lock_timeout; a wedged install that blocks Route) and confirmed green. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * fix(distributed): bound advisory-lock wait instead of disabling lock_timeout Setting lock_timeout = 0 to override a deployment's short global lock_timeout meant "wait forever" server-side. Safe for SmartRouter.Route (its loadCtx now carries the model-load ceiling) but unsafe for the schema-migration callers that pass context.Background(): a holder whose session never releases would hang them indefinitely. Derive the server-side lock_timeout from the caller's context instead: its remaining budget plus a margin (so the Go context's cancellation still wins with a clean error and the server bound is only a backstop), or a finite 30m backstop when the context has no deadline. Never zero - "wait forever" is no longer possible, while a deployment's hostile short lock_timeout is still overridden so legitimate cross-replica waits don't fail with 55P03. Added a spec proving a deadline-less waiter gives up at the (shrunk) backstop rather than hanging. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 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> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
f3d829e2ef |
feat(distributed): add LOCALAI_DISTRIBUTED_SHARED_MODELS to skip staging on shared volumes (#10556) (#10566)
In distributed mode, even when the frontend and workers share the same models directory via a shared volume mount, starting a model on a worker re-staged (re-downloaded) it: stageModelFiles always uploads model files into a tracking-key-namespaced subdir on the worker, and the staging probe only checks that staged location, so a file already present on the shared volume at the canonical path was never reused. Add a config switch LOCALAI_DISTRIBUTED_SHARED_MODELS (default false). When enabled, the operator asserts that all nodes mount the SAME models directory at the SAME path, so staging is unnecessary: the frontend's absolute model paths are already valid on the worker. In that mode stageModelFiles returns the cloned opts unchanged without uploading, leaving the path fields pointing at their canonical absolute paths so the worker loads them directly from the shared volume. The value is plumbed from DistributedConfig through SmartRouterOptions into the SmartRouter. Docs and docker-compose.distributed.yaml updated. 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
|
79783120dd |
fix(config): gate parallel-slot default on per-device VRAM too (#10485) (#10507)
The first #10485 fix (#10494) made the Blackwell physical-batch boost per-device/context-aware, which neutralized the big compute-buffer OOM, but the reporter's 2x16 GiB consumer Blackwell still OOM'd. Tracing the post-fix log: the model now loads its weights, builds the main context and warms up fine, and dies only on the *last* allocation — the MTP draft context's 800 MiB KV cache on the tighter device. #10411 changed only two defaults: the physical batch (now gated) and a VRAM-scaled parallel-slot count. The KV cache is unified (n_ctx_seq == full context proves slots share the budget, so parallel doesn't multiply KV), but n_seq_max=4 still adds per-slot compute-graph / context-checkpoint / output scratch. On a device packed ~99% by a 27B model spanning both cards, that overhead is the few-hundred-MiB straw — which is why reverting #10411 (and only #10411) restores a working load. Gate the parallel-slot default on the same per-device headroom predicate as the batch boost: when a large context already fills a single card (largeContextForDevice), keep n_parallel=1. A user running one big-context model that barely fits across two consumer GPUs is not serving four concurrent tenants. Small contexts and large unified-memory devices (GB10) keep full concurrency. Applied on both the single-host path and the distributed router. Also make the auto-tuning visible and reversible (the debugging here needed DEBUG logs and a git bisect): - Log the effective performance-relevant runtime options at INFO once per model load ("effective runtime tuning …": context, n_batch, n_gpu_layers, parallel, flash_attention, f16) so an admin can see what will run and pin or override any value in the model YAML. - LOCALAI_DISABLE_HARDWARE_DEFAULTS=true skips the hardware auto-tuning entirely (mirrors LOCALAI_DISABLE_GUESSING) for stock llama.cpp behavior. 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
|
0d6de15ae9 |
fix(config): per-device VRAM headroom for Blackwell defaults (#10485) (#10494)
The hardware-tuned defaults from #10411 were measured on a GB10 / DGX Spark (128 GiB unified memory) and over-provisioned multi-GPU consumer Blackwell (e.g. 2x16 GiB RTX 50-series) into CUDA OOM during model init: - The Blackwell physical batch (512 -> 2048) sets both n_batch and n_ubatch. The compute buffer scales ~n_ubatch * n_ctx and is allocated PER DEVICE (it can't be split across GPUs), so a large context turns ub2048 into multi-GiB of scratch that must fit one 16 GiB card. - The VRAM-scaled parallel-slot default tiered off TotalAvailableVRAM(), which SUMS all GPUs (2x16 -> "32 GiB" -> 8 slots), but the allocations are per-device. Make both decisions per-device and context-aware: - xsysinfo.MinPerGPUVRAM() reports the smallest device's VRAM; localGPU() uses it so the parallel tier and batch guard reason about one card. - PhysicalBatchForContext(gpu, ctx) raises the batch only when the extra compute buffer fits VRAM/4 at this model's context (16 GiB crosses over ~174k ctx, 32 GiB ~349k; GB10 reports system RAM so it still clears it). - Apply hardware defaults AFTER runBackendHooks in SetDefaults so the GGUF-guessed context is resolved before the batch decision. - The distributed router gates the node batch the same way. Unified-memory devices (GB10, Apple) report system RAM as their single device's VRAM, so they keep the prefill win. 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
|
682fb2718c |
fix(distributed): detach cold-load staging from the request context (#10438)
A model not yet loaded on a worker is staged lazily on the inference request path. Staging a multi-GB model takes minutes - far longer than any client keeps its HTTP request open - so a browser refresh, an ingress/LB idle-timeout, or a round-robined retry landing on another frontend replica cancels the request context and aborts the upload with "context canceled" mid-transfer. Large models then never finish staging, so they never load (observed in a 2-replica deployment: both frontends repeatedly failed to stage a 15.7 GB GGUF, each attempt dying at a different offset). Bind the cold load (staging + LoadModel + the per-model advisory lock) to context.WithoutCancel(ctx): it keeps the request's values (prefix chain) but drops cancellation/deadline. Each long step keeps its own bound (the file stager's resume budget, LoadModel's 5m timeout), and the advisory lock still de-dupes concurrent loaders across replicas. 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
|
b081247d95 |
feat(config): hardware-tuned defaults — Blackwell batch + VRAM-scaled concurrency (#10411)
* feat(config): node-aware hardware defaults — larger physical batch on Blackwell A larger physical batch (n_batch/n_ubatch) materially lifts MoE prefill on NVIDIA Blackwell consumer GPUs (sm_120/121, incl. GB10 / DGX Spark) — measured on a GB10 with Qwen3-Coder-30B-A3B, the prefill ceiling rises (ub512 ~2994 -> ub2048 ~3316 t/s) and saturates around 2048. The heuristic lives in core/config alongside the other config overriders (ApplyInferenceDefaults, guessDefaultsFromFile/NGPULayers) — they all fill the ModelConfig from heuristics, so hardware tuning is the same domain and stays in one place. It is parameterized on a GPU descriptor (not direct detection) so it works in both deployment shapes: - Single host: SetDefaults applies it with the LocalGPU. - Distributed: only the worker sees the GPU, so the worker reports its compute capability on registration (gpu_compute_capability -> BackendNode), and the router re-applies the SAME core/config heuristic for the SELECTED node before loading — fixing the case where the frontend has no GPU at all. Explicit `batch:` always wins (only managed default values are touched). xsysinfo gains NVIDIAComputeCapability() (detection only); all interpretation lives in core/config. Tests: core/config, pkg/xsysinfo, core/services/nodes. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(config): injectable local-GPU seam + single-instance coverage Make local GPU detection an injectable package var (localGPU) so the single-instance path (SetDefaults -> ApplyHardwareDefaults) is deterministically testable without a real GPU, mirroring the distributed override's coverage. Adds specs asserting SetDefaults sets the Blackwell physical batch, leaves it unset on non-Blackwell, and never overrides an explicit batch. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(config): default concurrent serving (n_parallel) by GPU VRAM The llama.cpp backend defaults n_parallel=1, which serializes multi-user requests and leaves continuous batching off (it auto-enables only at n_parallel>1). Fold a VRAM-scaled parallel-slot default into the hardware-config path so multi-user serving works out of the box: >=32GiB->8, >=8GiB->4, >=4GiB->2, else unchanged. With the backend's unified KV the slots SHARE the context budget, so this adds concurrency without multiplying KV memory. Explicit parallel/n_parallel always wins. EnsureParallelOption is shared by the single-host path (ApplyHardwareDefaults with the local GPU) and the distributed router (per selected node's reported VRAM, since the frontend may have no GPU). LocalGPU now also reports VRAM. Assisted-by: 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> |
||
|
|
e5c95e0449 |
fix(distributed): stage backend companion assets to remote nodes (#10330)
A model whose ModelFile is a single file (e.g. sherpa-onnx VITS/piper: the .onnx) failed to load on remote worker nodes because the sibling assets the backend resolves from the model dir — tokens.txt, lexicon.txt, the espeak-ng-data / dict directories, Kokoro's voices.bin — were never staged. Only the declared ModelFile was shipped, so the worker hit "failed to create sherpa-onnx TTS engine" and TTS produced no audio. Lean on the existing option-path staging instead of hardcoding filenames: - stageGenericOptions now also resolves an option value relative to the model's own directory (not just the frontend models dir), so a shared config can declare companions with bare names regardless of whether Model includes a subdirectory; and it expands directory-valued options (e.g. espeak-ng-data) file-by-file rather than handing a directory fd to the stager. - gallery/sherpa-onnx-tts.yaml declares the companion assets as option paths (tokens, lexicon, espeak-ng-data, voices.bin, dict, per-lang lexicons). The backend ignores these keys and keeps resolving siblings from the model dir; they exist only so distributed staging ships them. Absent files are skipped. Adds router_optionstage_test.go covering file + directory companion staging via the model-dir fallback. Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
92726f7631 |
fix(distributed): stage directory-based models to remote nodes (#10175)
Distributed file-staging treated every model path field (ModelFile, etc.) as a single regular file: it os.Open'd the path and streamed its fd as the HTTP PUT body. For directory-based models — e.g. qwen3-tts-cpp, whose weights and tokenizer ggufs live under one directory referenced by parameters.model — opening the directory succeeds but reading its fd returns EISDIR, so routing the model to a remote NATS worker failed with "read /models/<model>: is a directory". Single-file models were unaffected, so only multi-file pipelines (e.g. the realtime TTS stage) broke. stageModelFiles now detects a directory path field and stages each contained file individually (via the new stageDirectory helper), preserving structure with the existing StagingKeyMapper and rewriting the field to the remote directory (deriving ModelPath as before). countStageableFiles makes the progress total count a directory's files so the staging tracker stays accurate. Assisted-by: Claude:claude-opus-4-8 go vet Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
a44bdb29d4 |
feat: prefix-cache-aware routing for distributed mode (#10071)
* feat(radixtree): generic prefix tree skeleton with longest-match Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(radixtree): Insert with path recency refresh and entry cap Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(radixtree): TTL idle-expiry and Evict sweep with branch pruning Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(radixtree): recency-weighted per-value Weight Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(radixtree): Remove all entries for a value Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(radixtree): race-free concurrency smoke test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(radixtree): reclaim empty branches, RWMutex reads, TTL boundary, empty-key guard Address review findings on the generic prefix tree: - Extract a shared pruneWalk helper parameterized by a shouldClear predicate and use it from Evict, Remove, and the MaxEntries path. Previously evictOldestLocked cleared a victim's value but never removed the now value-less node or its childless ancestors, so internal nodes accumulated under sustained churn at the cap. The MaxEntries path now prunes the victim and its empty ancestors. - DRY: pruneWalk replaces the duplicated logic in the former pruneLocked and Remove's inner closure. - Switch Tree.mu to sync.RWMutex; LongestMatch, Weight and Len take the read lock (RLock) while Insert, Evict and Remove keep the write lock. Confirmed race-clean under go test -race. - Document the strict greater-than TTL boundary on Options.TTL and expired: age exactly equal to TTL is still live. - Guard Insert against an empty key (no-op): the root never holds a value. Adds Ginkgo specs covering MaxEntries eviction, ancestor reclamation, the no-growth-past-cap invariant, the TTL boundary, and empty-key behavior for both Insert and LongestMatch. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): RoutePolicy enum with parse/resolve Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): Config with defaults and validation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): deterministic xxhash prefix-chain extractor Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): pure filter-then-score replica selection Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): Provider interface and radix-tree-backed Index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(prefixcache): gofmt policy enum comment alignment Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): head-first prefix chunking and hoist Weight out of sort Address code-quality review findings in the prefixcache package. Correctness: ExtractChain now chunks from absolute offset 0 with fixed [0,W),[W,2W),... boundaries and caps the chain to the FIRST MaxDepth head blocks. The previous tail-keeping logic shifted the byte offset by a non-window amount once a conversation grew past MaxDepth*WindowBytes, changing every hash each turn and silently breaking cross-turn longest-prefix matching. The reusable KV/prefix cache lives at the head of the prompt, so anchoring at offset 0 makes the chain a true prefix-chain: P and P+suffix share their full leading overlap. Add a regression spec proving cross-turn stability past the cap. Performance: Index.Decide precomputes each candidate's Weight once (decorate-sort-undecorate) instead of calling the O(tree size) Weight inside the O(n log n) sort comparator. Behavior is unchanged. Lint: encode prev with binary.LittleEndian.PutUint64 instead of a manual byte loop, clearing the modernize rangeint finding. Also add a concurrent Decide/Observe/Invalidate spec to exercise Index's documented concurrency safety under go test -race. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): prefixcache observe/invalidate subjects and payloads Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): NATS sync publish/apply for observe and invalidate Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributedhdr): ctx carrier for prefix-hash chain Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributedhdr): PrefixChainHook indirection for backend-side chain build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(backend): stash prompt prefix chain on ctx before distributed routing Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(backend): mirror modelID fallback for prefix-chain salt parity Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): scheduling config columns for prefix-cache routing Add RoutePolicy and per-model balance/prefix-match override columns to ModelSchedulingConfig and include them in the SetModelScheduling upsert DoUpdates list so updates are not dropped on conflict. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): optional route preference in FindAndLockNodeWithModel Add a RoutePreference type and a new pref parameter so the atomic pick+lock+increment can be biased toward a preferred node without weakening atomicity. A nil preference reproduces the previous ORDER BY behavior exactly. Update the ModelRouter interface, both router.go call sites (pass nil for now; Phase 5 builds the real preference), the test doubles, and the distributed e2e caller. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): make Sync satisfy Provider with Evict Sync.Observe now returns whether the local index treated the assignment as new or extended, and Sync gains an Evict method that delegates to the wrapped index. Together these let SmartRouter hold a single prefixcache.Provider that broadcasts via NATS. Adds a compile-time Provider assertion and an Evict-delegates behavioral test. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): prefix-cache-aware preference and observe in SmartRouter.Route Add a PrefixProvider + PrefixConfig to SmartRouterOptions/SmartRouter (nil keeps routing byte-for-byte the round-robin floor). On each request Route now calls buildPreference: it reads the prompt prefix chain from ctx (distributedhdr.PrefixChain), resolves the per-model policy/thresholds over the global config, loads candidate replica in-flight via a new registry read LoadedReplicaStats (deduped to one entry per node using the MIN in-flight across that node's replicas), asks the provider to Decide, and runs prefixcache.Select. The chosen node is passed as the RoutePreference to FindAndLockNodeWithModel on all three pick paths (cache hit, locked re-pick, cold scheduleAndLoad), and the served node is recorded via Observe only when the resolved policy is prefix_cache so round-robin models never pollute the tree. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): invalidate prefix-cache entries on unload and stale removal UnloadModel and both staleness fall-through paths in Route (after a failed gRPC probe and RemoveNodeModel) now call prefixProvider.Invalidate(model, nodeID), guarded by a nil-provider check so the round-robin floor is unchanged. At runtime the provider is the *prefixcache.Sync, so invalidations also broadcast to peer frontends. Adds a test that a previously hot prefix no longer Decides to a node after UnloadModel. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(prefixcache): rolling forced-disturb pressure counter Add a concurrency-safe per-model rolling counter that tracks how many times a request had a usable hot prefix match but the load guard forced it off the warm node. Entries outside the window are dropped lazily on Count so the backing slice stays bounded. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): autoscale on prefix-cache forced-disturb pressure Wire the rolling forced-disturb counter into the SmartRouter and the ReplicaReconciler. Router: in buildPreference, after Decide + Select, record a forced-disturb when a usable hot prefix match existed (d.HotNodeID != "" and d.MatchRatio >= cfg.MinPrefixMatch) but Select chose a different node (or nothing) because the load guard ruled the warm node out. This is the scale-worthy signal: the cache-warm replica is saturated. It deliberately does not fire for all-unique workloads (no hot match), avoiding false-positive scale-ups. Pressure is optional on SmartRouterOptions; nil keeps the path a no-op. Reconciler: read the same Pressure instance in reconcileModel as an extra scale-up reason, reusing the existing MaxReplicas + ClusterCapacityForModel guards and the UnsatisfiableUntil cooldown that gates the whole method. Pressure never overrides MaxReplicas and never force-evicts; a no-capacity model does not spin. Window and threshold come from prefixcache.Config (PressureWindow default 1m, PressureScaleThreshold default 1) and are configurable via ReplicaReconcilerOptions. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): bound Pressure slice in Record; drop dead reconciler pressureWindow Record now prunes entries older than the rolling window (the same prune Count does), via a shared pruneLocked helper, so a model that takes forced-disturb records but is never Counted (e.g. one with zero loaded replicas the reconciler skips) no longer grows its backing slice unbounded. Also removes the dead pressureWindow struct field and the ReplicaReconcilerOptions.PressureWindow option from the reconciler: they were stored but never read (the window lives inside the *prefixcache.Pressure instance). The scale block now reads pressure.Count once into a local. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(api): prefix-cache fields in scheduling endpoint DTO with validation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): prefix-cache routing controls in node scheduling form Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): wire prefix-cache index, NATS sync, and config Activates prefix-cache-aware routing in distributed mode. Builds the prefixcache Index + NATS-backed Sync + Pressure counter, installs the distributedhdr.PrefixChainHook so core/backend/llm.go attaches a prefix chain per request, subscribes to prefixcache.observe/prefixcache.invalidate to apply peers' events to the local index (no re-broadcast), threads PrefixProvider/PrefixConfig/Pressure into the SmartRouter and Pressure/PressureThreshold into the ReplicaReconciler, and runs a background eviction ticker (every TTL/2) bound to the app context. Enabled by default; --distributed-prefix-cache=false (LOCALAI_DISTRIBUTED_PREFIX_CACHE) opts out and leaves the provider/pressure nil so routing stays round-robin. --distributed-prefix-cache-ttl (LOCALAI_DISTRIBUTED_PREFIX_CACHE_TTL, default 5m) controls entry idle-timeout and eviction cadence. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(nodes): round-robin-floor invariant for prefix-cache routing Drives Select directly: a saturated hot node (in_flight 50 vs 0) is never picked even with a perfect prefix match (round-robin floor holds), while a balanced hot node within the load slack is reused. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(prefixcache): clear branch lint findings and em dashes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): validate prefix-cache config at startup wiring Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * perf(radixtree): single-walk WeightsFor for batch value weights Add Tree.WeightsFor(values, now) which computes the recency-weighted weight for many values in a single O(N + len(values)) tree traversal, versus calling Weight once per value (O(len(values) * N)). Consumers that score K candidates against the tree under the read lock no longer pay K full walks. Extract the per-entry contribution math into an unexported helper shared by both Weight and WeightsFor so the metric stays identical (DRY). Weight's public behavior is unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(config): add ModelConfig.ModelID() single source of truth The c.Name fallback to c.Model was duplicated in core/backend/options.go (feeding model.WithModelID) and hand-copied into core/backend/llm.go (the prefix-chain salt). These MUST agree or the prefix-cache salt diverges silently from the id the model loader tracks. Consolidate both into a new config.ModelConfig.ModelID() helper and call it from both sites. Behavior is identical. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * perf(prefixcache): reuse one xxhash.Digest in ExtractChain ExtractChain allocated a fresh xxhash.New() Digest per block (up to MaxDepth per call) and grew the chain slice without preallocation. Reuse a single Digest via Reset() before each block and preallocate the chain to min(nBlocks, MaxDepth). xxhash seed 0 is stateless, so Reset()+Write produces the byte-identical value to a fresh New()+Write. Output hashes are unchanged, preserving the cross-process determinism that peers rely on over NATS. Verified by capturing ExtractChain output for the existing test inputs before and after the refactor: identical. Existing extractor tests pass unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): drop hot match when matched node is not a candidate; weigh cold candidates in one walk Index.Decide called radixtree.LongestMatch over the whole tree, so the deepest match could be a node that is offline, unloaded, or simply not in the passed candidate set. Honoring that as HotNodeID produced a false forced-disturb signal upstream (buildPreference records pressure when chosen != HotNodeID), making it look like a warm replica was load saturated when it was actually absent. Build the candidate set once and only set HotNodeID/MatchRatio when the matched node is an actual candidate; otherwise fall back to cold placement. A future refinement could ask the tree for the longest match restricted to the candidate nodes (shallower-but-valid) instead of dropping it. Also replace the per-candidate tree.Weight call in the cold-order sort with a single tree.WeightsFor walk, turning O(K*N) under the read lock into O(N + K). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(prefixcache): remove Select's unreachable deterministic fallback buildPreference always passes ColdOrder as a permutation of the full candidate set, so the cold-order loop hits every eligible candidate. The trailing best/bestIF scan was dead. Replace it with a plain "return """ and document that ColdOrder is guaranteed to cover all candidates, so "" means none were eligible. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): fetch model scheduling config once per Route GetModelScheduling was read three times per request - in resolveSelectorCandidates, buildPreference, and nodeMatchesScheduling - three DB round-trips for one row that is immutable for the life of the request, and not a consistent snapshot. Fetch it once near the top of Route and thread the *ModelSchedulingConfig (may be nil) into all three helpers. scheduleNewModel keeps its own fetch since it runs outside the Route snapshot. Behavior is identical for nil sched. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(autoscale): add Pressure.Reset to consume forced-disturb signal Pressure.Count is non-draining (it prunes only by age), so a single burst of forced-disturbs stays within the rolling window for the whole window and keeps Count >= threshold on every reconciler tick. The reconciler will use Reset to clear a model's events after acting on the signal so a fresh scale-up requires fresh forced-disturbs to accumulate, rather than one burst driving the model toward MaxReplicas. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(autoscale): at most one scale-up per reconcile tick, consume pressure Two autoscale bugs: 1. Over-scaling: the pressure scale-up block read Pressure.Count but never consumed it. With a non-draining counter a single forced-disturb burst kept Count >= threshold across the whole window, firing scaleUp on every tick and pushing the model toward MaxReplicas off one transient burst. After a successful pressure-triggered scale-up the reconciler now calls Pressure.Reset to consume the signal. 2. Double scale-up in one tick: the all-replicas-busy block and the pressure block could both fire in the same reconcileModel pass, each calling scaleUp(+1) against the same `current` read once at the top, so a model that was both busy and over threshold scaled +2 and could overshoot MaxReplicas by one. A scaledUp flag now enforces at most one scaleUp(+1) per tick: the pressure block is skipped if the busy block already scaled, and scale-down is skipped in any tick that scaled up. MinReplicas enforcement, UnsatisfiableUntil backoff, and capacity guards are unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(nodes): replica-removed chokepoint hook for prefix-cache invalidation Add SetReplicaRemovedHook to NodeRegistry and fire it from both RemoveNodeModel and RemoveAllNodeModelReplicas after a successful delete. This is the single chokepoint every replica-removal path funnels through (router eviction, reconciler scale-down, probe reaper, health-monitor node-down reap, RemoteUnloaderAdapter), so the prefix-cache index can be invalidated by construction rather than wiring each call site individually. The hook is stored in an atomic.Pointer so the startup wiring (setter) and the request/reconcile-time fire are race-free; it is nil-safe when unset. GORM Delete reports no error for a no-op delete, so the hook also fires when nothing was removed; the consumer's Invalidate(model, node) is idempotent so this is harmless. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): invalidate prefix-cache on any replica removal via registry hook Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(prefixcache): single source of truth for threshold bounds Extract ValidateThresholds into prefixcache/config.go so the per-model override validation (nodes.go endpoint) and Config.Validate share one implementation of the numeric bounds (min_prefix_match in [0,1], balance_abs_threshold >= 0, balance_rel_threshold == 0-or->= 1) instead of hard-coding them in two places. The route_policy allow-list stays explicit (not ParsePolicy, which maps typos to Default). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(nodes): preserve prefix-cache settings on partial scheduling update A scheduling POST that omitted route_policy/thresholds (e.g. a min_replicas-only update) full-replaced every column and silently reset the model's previously-configured prefix-cache settings to empty/zero. Make the four prefix-cache request fields pointers so omitted is distinguishable from explicit zero, and merge PATCH-style in SetSchedulingEndpoint: a provided pointer wins, an omitted one preserves the existing config value (zero default when none). Non-prefix fields keep their full-replace PUT semantics. Validation now runs on the resolved values via prefixcache.ValidateThresholds. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): make Invalidate a no-op for uncached models and skip empty broadcasts A registry chokepoint fires Sync.Invalidate(model, nodeID) for every replica removal of every model, including round-robin models that never used the prefix cache. Index.Invalidate previously called tree(model), which lazily created and permanently retained an empty radix tree for any model that ever lost a replica, growing the trees map without bound. Sync.Invalidate also published a NATS PrefixCacheInvalidateEvent on every call, amplifying no-op removals across the cluster. Index.Invalidate now looks the tree up read-only via existingTree and returns without allocating when none exists. The Provider interface is unchanged; Sync gates the broadcast through an optional invalidateExisting(bool) capability type-asserted from the wrapped Index, falling back to the prior always-broadcast behavior for other Provider implementations. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * perf(prefixcache): derive Decide candidacy from WeightsFor and skip trivial sort WeightsFor already returns a map keyed by every requested candidate, so the separate candidates set built to validate the hot match was redundant: a node is a candidate iff it is a key in the weights map. Drop the extra map and gate the hot-match check on weights membership. Also skip the sort when there is at most one candidate, since the input order is already the cold order. Behavior is unchanged. Deferred follow-up: skipping the WeightsFor walk entirely when a hot match wins would need lazy cross-file changes and is out of scope here. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(nodes): fire replica-removed hook on bulk node_models deletes; trim LoadedReplicaStats columns Bulk node-scoped node_models deletes (Register re-register cleanup, MarkOffline, MarkDraining, Deregister) removed rows directly without firing the replica-removed hook, so the prefix-cache index kept pointing at nodes whose models were gone. Capture the DISTINCT model names before each bulk delete and fire fireReplicaRemoved once per model after a successful delete, restoring the single-chokepoint invariant for all removal paths. The pre-query is skipped when no hook is set so the no-hook path stays cheap. Also narrow LoadedReplicaStats to SELECT only node_id and in_flight (the only fields the router consumer reads), dropping the JOIN-side available_vram fetch and unused columns while keeping the []ReplicaCandidate return type unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(reconciler): consume autoscale signals only on a real scale-up scaleUp was fire-and-forget (void) yet its callers unconditionally consumed the pressure signal (Pressure.Reset) and the MinReplicas hysteresis (ClearUnsatisfiable) right after calling it. If scaleUp added nothing (ScheduleAndLoadModel errored, or no node could be loaded) the saturated warm replica got no new replica AND its accumulated forced-disturb history was wiped, forcing the signal to re-accumulate over a full PressureWindow before the next attempt. Make scaleUp return whether at least one replica was actually scheduled, and gate the side effects on it: - pressure block (2b): set scaledUp and call Pressure.Reset only on success; on failure preserve the signal so the next tick retries off the same accumulated pressure. - busy-burst block (2): set scaledUp from the return value so a failed attempt does not suppress the pressure path or scale-down. - MinReplicas block: call ClearUnsatisfiable only on success so a failed attempt does not reset the unsatisfiable counter. All existing invariants (MaxReplicas, capacity gating, UnsatisfiableUntil cooldown, at-most-one-scale-up-per-tick) are preserved. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(nodes): drop router's redundant prefix-cache Invalidate calls The NodeRegistry removal chokepoint (RemoveNodeModel / RemoveAllNodeModelReplicas) now fires SetReplicaRemovedHook, which invalidates the prefix-cache index. The router was also calling prefixProvider.Invalidate explicitly right after each registry removal on the two stale-replica health-probe fall-throughs in Route and in UnloadModel, so every router-side eviction invalidated twice (double tree-prune + double NATS broadcast). Remove the three redundant explicit Invalidate calls and their empty nil-guards. Each removed call sat immediately after a registry removal that fires the hook, so invalidation is preserved via the chokepoint. Decide/Observe usage is untouched. Re-point the unit test (fake registry fires no hook) to assert the removal chokepoint is exercised on unload instead of the router's direct invalidation. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): broadcast invalidations unconditionally for cross-frontend coherence Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(prefixcache): reject TTL<=0 in Config.Validate (eviction ticker would panic) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(nodes): make capture+delete atomic in bulk node_models removal paths MarkOffline, MarkDraining, and the Register re-register cleanup ran the nodeModelNames SELECT and the bulk node_models DELETE as two separate statements on r.db with no transaction. A SetNodeModel landing between the two was deleted but its replica-removed hook never fired, leaving the prefix-cache index pointing at a removed replica until TTL or candidacy self-heal. Wrap the capture and the delete in a single db.Transaction in each path (mirroring how Deregister already does it). The captured model names are collected into a slice declared outside the closure; the replica-removed hook fires for each only after the transaction commits, so a rollback never invalidates the index for a removal that did not persist. The set of fired hooks now equals exactly the set of node_models rows actually deleted, with no interleaving gap. The status flip in MarkOffline/MarkDraining (setStatus) is a separate, pre-existing operation and routing already filters non-healthy nodes, so it stays outside the transaction; return contracts are unchanged. Deregister was already correct and is untouched. The cheap-path skip (no hook -> skip the SELECT) is preserved. Adds a spec asserting MarkOffline fires hooks for exactly the rows it deletes and leaves no node_models row behind (consistent snapshot). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(nodes): debug logging for prefix-cache routing decisions and observations Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(radixtree): match shared prefixes by valuing every node on insert Insert recorded the value (node id) only on the final node of the key chain, leaving every intermediate prefix node valueless. LongestMatch returns the deepest node that hasValue, so two chains that share a leading block but diverge in the tail never matched: only exact-repeat queries hit. That broke the prefix-cache routing core use cases (shared system prompt, multi-turn extension, volatile tail), all of which rely on prefix matching rather than exact-repeat. Set value/hasValue/lastSeen at every node along the chain so each prefix-block node remembers the node id that served that prefix (SGLang/vLLM-style). The deepest match wins, and the last writer owns a shared prefix node (a recency heuristic: the most recent chain through a block is the one most likely still warm). size now counts valued nodes, which is the intended meaning. Updated radixtree tests to the new semantics: deepest-prefix test uses non-overlapping chains, a new test asserts last-writer-owns-shared-node, Evict/Remove/MaxEntries expectations recomputed for per-prefix-node counting, and a shared-prefix LongestMatch red test added. Added a prefixcache Decide test proving a prefix-only query routes to the warm node. No prefixcache .go logic changed. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): lock in prefix-cache routing behavior end to end Add a DB-backed e2e spec that drives SmartRouter against a real NodeRegistry (Postgres testcontainer) and the real prefixcache.Index radix-tree provider, using a fake gRPC backend factory so no real inference runs. Covers the five behaviors validated by hand: 1. Cold miss + observe: an unseen prefix chain cold-places and is recorded. 2. Hot-match affinity: the same chain returns to its warm node X. 3. Shared-prefix match: a divergent chain sharing X's leading prefix still routes to X (the radix-tree regression we fixed). 4. Negative control: an unrelated chain is a cold miss, not a false hot match on X. 5. Failover + invalidation: removing X's replica fires the registry chokepoint hook to invalidate the prefix entry, and the chain fails over to surviving node Y and re-homes there. Replaces the need for manual docker-compose re-runs. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(prefixcache): make prefix-cache affinity replica-granular Track prefix-cache affinity per loaded replica (a backend process with its own KV cache) instead of per node, so multiple replicas of the same model on one node each keep distinct affinity and a hot prefix routes back to the exact replica that served it. - radixtree: add RemoveFunc(pred) and reimplement Remove on top of it. - prefixcache: introduce ReplicaKey{NodeID, Replica}; Index/Candidate/ PrefixDecision/Select/Provider now key on ReplicaKey. Add InvalidateNode to drop every replica of a node; Invalidate drops one replica. Select returns (ReplicaKey, bool) and gains a deterministic least-in-flight eligible fallback (tiebreak NodeID then Replica). - messaging: carry Replica on PrefixCacheObserveEvent and PrefixCacheInvalidateEvent (Replica < 0 means all replicas of the node). - Sync delegates + broadcasts with replica; InvalidateNode broadcasts Replica=-1; ApplyInvalidate routes negative replica to InvalidateNode. This is part 1 of 2; the registry/router/wiring consumers are updated separately. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): make prefix-cache routing replica-granular Wire the SmartRouter, NodeRegistry, and distributed startup to the replica-keyed prefixcache API. Affinity is now tracked per replica (each replica is a separate process with its own KV cache), so a prefix served by (node,0) no longer leaks onto the same-node sibling (node,1). - RoutePreference gains PreferredReplica; FindAndLockNodeWithModel locks the EXACT (node_id, replica_index) row, falling through to the default ORDER BY when that replica is not loaded. - SetReplicaRemovedHook now carries replicaIndex; RemoveNodeModel fires the specific replica, RemoveAllNodeModelReplicas and the four bulk node-scoped deletes fire replica<0 (all replicas of the node). - buildPreference builds one Candidate per loaded replica and locks the exact replica the policy chose; observePrefix records the served ReplicaKey at every call site. - distributed.go routes the hook to InvalidateNode (replica<0) or Invalidate(key). - Tests updated to the replica-keyed API plus new coverage: a hot prefix on (node,0) prefers replica 0 over the same-node sibling (router unit + e2e), and FindAndLock locks the exact preferred replica. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): derive prefix chain from messages for tokenizer-template models Prefix-cache-aware routing built its prompt-prefix chain from the rendered prompt string `s` in ModelInference. For models with TemplateConfig.UseTokenizerTemplate the frontend never renders a prompt - the backend tokenizes the structured messages itself - so `s` is empty, the chain is empty, and routing silently falls back to round-robin. That covers the bulk of modern chat models (qwen3, llama3, ...), so the feature effectively never engaged for them. Fall back to messagesPrefixSource(messages): a deterministic, prefix-stable head-first serialization of the conversation (role + content per turn). Two requests sharing a leading system prompt and early turns share a leading byte prefix, which ExtractChain maps to a shared chain prefix - landing both on the same cache-warm replica. The rendered `s` is still preferred when present (higher fidelity for non-template models). Found via the multi-replica-per-node e2e: zero "prefix-cache routing decision" logs despite per-request Route calls, traced to the empty-chain guard. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document prefix-cache routing roadmap Add a routing-and-caching roadmap section to the distributed-mode guide, linking the epic (#10063) and the follow-up issues (#10064-#10070) surfaced from a survey of SGLang, vLLM production-stack, Ray Serve, llm-d, AIBrix, and NVIDIA Dynamo. 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
|
a891eedd08 |
fix(distributed): persist per-model load info so reconciler survives frontend restart (#9981)
* feat(distributed): add per-model ModelLoadInfo persistence
Adds a dedicated ModelLoadInfo table keyed by model name, decoupled from
the per-replica NodeModel rows. The reconciler can now recover model load
metadata after every NodeModel row has been removed (worker death,
eviction, MarkOffline reaping, frontend restart with stale heartbeats),
which is the read side of Bug-1 from the distributed mode bug hunt.
Registry exposes:
- UpsertModelLoadInfo: ON CONFLICT (model_name) update; last-write-wins,
matching the existing per-replica blob semantics under concurrent
multi-frontend dispatch.
- GetModelLoadInfo: read from the new table first; fall back to the
legacy NodeModel-blob scan for rows written before any frontend in
the cluster ran an UpsertModelLoadInfo (rolling-upgrade transition).
SetNodeModelLoadInfo (per-replica blob) is preserved for backward
compatibility and per-replica diagnostics; the dispatch-path hook in the
next commit calls both.
The new table joins the existing nodes AutoMigrate set under the same
schema-migration advisory lock.
Refs: Bug-1, docs/superpowers/specs/2026-05-24-distributed-mode-bug-hunt-findings.md
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7[1m]
* fix(distributed): persist per-model load info on dispatch
scheduleAndLoad now writes the (backendType, ModelOptions blob) pair to
the new ModelLoadInfo table in addition to the existing per-replica
NodeModel.model_opts_blob field. The per-replica blob still works for
the hot path; the per-model row outlives every NodeModel row going away,
which is what unblocks the reconciler on the read side.
Both writes are best-effort with warn-level logging on failure: a write
miss here just means the reconciler may need a fresh inference request
to repopulate, which is the pre-fix behavior.
Concurrency: two frontends loading the same model at the same time both
fire UpsertModelLoadInfo; ON CONFLICT (model_name) makes the row
converge to whichever commits last. Matches the existing per-replica
blob semantics.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7[1m]
* test(distributed): cover load info persistence and Bug-1 recovery
Adds Ginkgo specs that prove the persistence layer behaves correctly and
that the reconciler actually recovers from the frontend-restart scenario
that was failing in production:
registry_test.go:
- per-model row survives RemoveAllNodeModelReplicas (the bug repro)
- ON CONFLICT (model_name) updates backend type + blob, last-write-wins
- legacy NodeModel-blob fallback still works (rolling-upgrade transition)
- GetModelLoadInfo returns ErrRecordNotFound when both sources are empty
- UpsertModelLoadInfo rejects empty model names
reconciler_test.go:
- Bug-1 end-to-end: with min_replicas=2, no NodeModel rows, but a
ModelLoadInfo row present, one reconcile tick fires two scheduler
calls. Pre-fix this returned "no load info" and the scheduler never
got called until a fresh inference request arrived.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7[1m]
* docs(distributed): note restart-safe reconciler behavior
Adds a bullet to the Replica Reconciler section explaining that per-model
load metadata is persisted across frontend restarts via the new
model_load_infos PostgreSQL table, so a rolling upgrade no longer needs a
fresh inference request per model before the reconciler can replace dead
replicas.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7[1m]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
LocalAI [bot]andEttore Di Giacinto
|
8bbe89a537 |
fix(distributed): route per request across loaded replicas + cache probeHealth (#9968)
* refactor(distributed): extract PickBestReplica from FindAndLockNodeWithModel Lifts the replica-selection policy (in_flight ASC, last_used ASC, available_vram DESC) out of the SQL ORDER BY into a pure Go function in the new replicapicker.go. The SQL clause keeps its FOR UPDATE atomicity and remains the production path used by SmartRouter; PickBestReplica is the canonical implementation that the future per-frontend rotating replica cache (TODO referenced from pkg/model) will call against an in-memory snapshot without paying a DB round-trip per inference. A new registry_test mirror spec seeds a multi-tier scenario and asserts both layers pick the same replica, so any future tweak to either side fails the test until the other side is updated. No behavior change. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-7 [Claude Code] * fix(distributed): route per inference request and cache probeHealth Two related fixes that together restore load balancing across loaded replicas of the same model. 1. ModelLoader.Load and LoadModel bypass the local *Model cache when modelRouter is set. The cached *Model wraps an InFlightTrackingClient bound to a single (nodeID, replicaIndex) — reusing it pinned every subsequent request to whichever node won the very first pick, so FindAndLockNodeWithModel's round-robin never got a chance to run even after the reconciler scaled the model out to a second node. In distributed mode SmartRouter.Route now runs per request, and PickBestReplica picks the least-loaded replica each time. SmartRouter has its own coalescing (advisory DB lock for first-time loads + singleflight on backend.install RPC) so concurrent first requests for a not-yet-loaded model still produce a single worker side install. 2. SmartRouter.probeHealth memoizes successful gRPC HealthCheck results in a new probeCache (probe_cache.go) with a 30s TTL. With per-request routing every inference call hits probeHealth, and llama.cpp-style backends serialize HealthCheck behind active Predict — so a burst of incoming requests stalled on the probe to a node already mid-stream, tripping the 2s timeout and falling through to the install path. singleflight collapses N concurrent first-time probes for the same (node, addr) into one round-trip, failed probes invalidate the entry so the staleness-recovery path still triggers, and the TTL matches pkg/model/model.go's healthCheckTTL so the single-process and distributed paths share a staleness budget. The background HealthMonitor still reaps actually-dead backends within ~45s. The bypass introduces one short FindAndLockNodeWithModel transaction per inference. A TODO in pkg/model/loader.go documents the future per modelID rotating-replica cache that would reuse PickBestReplica against an in-memory snapshot and skip the DB round-trip for hot paths. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-7 [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
|
a0f3e26245 |
fix(distributed): make admin backend installs resilient and observable (#9958)
* feat(distributed): add configurable NATS backend install/upgrade timeouts Adds BackendInstallTimeout and BackendUpgradeTimeout to DistributedConfig with 15m defaults, following the existing MCPToolTimeout / WorkerWaitTimeout pattern. These will replace the hardcoded literals in RemoteUnloaderAdapter so admin-driven backend installs across the cluster survive long OCI image pulls that previously timed out at 3m. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(distributed): gofmt alignment after timeout fields Re-aligns the Validate() negative-duration map and the Default* const block so the new BackendInstall/UpgradeTimeout entries do not leave the surrounding columns mis-padded. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(cli): surface LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT and _UPGRADE_TIMEOUT Parses the two new env vars on the run CLI and threads them through the existing AppOption builder so DistributedConfig picks them up. Invalid duration strings now fail loudly at startup rather than silently falling back to the default. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): inject NATS install/upgrade timeouts into RemoteUnloaderAdapter Removes the hardcoded 3m / 15m literals from RemoteUnloaderAdapter and threads in DistributedConfig.BackendInstallTimeoutOrDefault() and BackendUpgradeTimeoutOrDefault() at construction. Install now defaults to 15m (was 3m); cold OCI image pulls on Jetson Wi-Fi routinely blew past the old ceiling. Scripted messaging client captures the timeout so tests can assert the configured value actually reaches the NATS request. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): introduce galleryop.ErrWorkerStillInstalling sentinel When the NATS request-reply for backend.install (or .upgrade) times out the worker is almost always still pulling the OCI image. Wrap the timeout in a typed sentinel so the manager above can distinguish "worker hung" from "worker still working" and leave the pending_backend_ops row in place for the reconciler to confirm via backend.list. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): treat NATS install timeout as in-progress, not failure When a worker times out replying to backend.install but the install is still running on the worker, enqueueAndDrainBackendOp now reports a running_on_worker status and pushes NextRetryAt out by the install timeout so the reconciler does not immediately re-fire another install while the worker is still pulling the image. The pending_backend_ops row stays in place for the next reconciler pass to confirm via backend.list. InstallBackend wraps the result in galleryop.ErrWorkerStillInstalling so callers can branch (galleryop renders yellow in-progress instead of red error). UpgradeBackend uses the same wrap. Adds RemoteUnloaderAdapter.InstallTimeout() so the manager can push NextRetryAt by the configured timeout without reaching into a private field, and NodeRegistry.RecordPendingBackendOpInFlight as the soft cousin of RecordPendingBackendOpFailure. Also includes incidental gofmt-driven struct-field alignment in registry.go on lines unrelated to the change (touched files are re-formatted to canonical form per project policy). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): don't increment Attempts on in-flight install timeout An in-flight timeout (worker still pulling the OCI image) is not a failed attempt, it's a delayed one. Incrementing Attempts let genuinely-progressing slow installs (e.g. 30 GB CUDA images on Wi-Fi) trip the reconciler's maxPendingBackendOpAttempts cap and dead-letter the queue row while the worker was still legitimately working. RecordPendingBackendOpInFlight now only updates LastError and NextRetryAt. Also documents "running_on_worker" in the NodeOpStatus.Status enum comment so Task 6 implementers see the full surface. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): surface ErrWorkerStillInstalling as non-error OpStatus When the distributed backend manager returns an error that wraps ErrWorkerStillInstalling, backendHandler now completes the op with a "still installing in background" message rather than marking it as a red failure. Admin UI sees a yellow in-progress state; reconciler confirms completion on its next pass. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): end-to-end install-timeout-then-reconcile Wires Task 1-6 end-to-end so any seam mismatch surfaces in CI rather than during a real cluster install. NATS times out, the queue row stays alive with running_on_worker status, the worker eventually reports the backend installed via backend.list, the manager surfaces it via ListBackends. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT / _UPGRADE_TIMEOUT Add the two new operator-tunable env vars to the Frontend Configuration table in the distributed-mode docs. Explains the 15m default, when to raise it (slow links pulling multi-GB OCI images), and the new "still installing in background" admin-UI state when the round-trip times out but the worker is still working. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): clear pending install rows when backend.list confirms DistributedBackendManager.ListBackends now proactively clears pending_backend_ops install rows whose (nodeID, backend) is reported installed by backend.list. Operator UI updates immediately instead of waiting up to installTimeout (default 15m) for the next reconciler tick after NextRetryAt. Only install rows are cleared; upgrade and delete intents are not satisfied by presence in backend.list and continue to drain through their normal reconciler paths. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): add BackendInstallProgressEvent wire type and subject New NATS subject nodes.<nodeID>.backend.install.<opID>.progress lets the worker publish transient progress events (file, current/total bytes, percentage, phase) while a long-running install pulls its OCI image. BackendInstallRequest gains an optional OpID field so the worker knows which subject to publish on. Transient pub/sub (not JetStream): the install reply remains ground truth for success/failure; dropped progress events are tolerable. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(messaging): drop em-dash from BackendInstallProgress test comment Per project convention (no em-dashes anywhere). Comment substance is unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): worker publishes debounced install progress over NATS When BackendInstallRequest.OpID is set, the worker's backend.install handler wires a debounced publisher (250ms window) into the gallery download callback. Each tick becomes a BackendInstallProgressEvent on nodes.<nodeID>.backend.install.<opID>.progress; the publisher always emits a final event on Flush so the UI sees the terminal percentage. Old masters that do not set OpID continue to run silent installs: no behavior change for them. Lock ordering: the publisher releases its mutex before calling messaging.Publish so a slow network never stalls the install loop. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): RemoteUnloaderAdapter subscribes to install progress InstallBackend gains opID + onProgress parameters. When both are set, the adapter subscribes to nodes.<nodeID>.backend.install.<opID>.progress BEFORE publishing the install request, decodes each message into the caller's onProgress callback in a goroutine (so a slow callback never stalls the NATS reader thread), and unsubscribes after RequestJSON returns. When onProgress is nil OR opID is empty (the reconciler retry path), subscription is skipped entirely - silent installs cost nothing extra. Subscribe failure is logged at Warn and the install proceeds without progress streaming; the NATS round-trip still owns terminal status. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): forward backend install progress into galleryop OpStatus DistributedBackendManager.InstallBackend now passes the gallery op ID and a progress bridge into the adapter call. Each BackendInstallProgressEvent from the worker becomes a galleryop.ProgressCallback tick - which the existing backendHandler already turns into OpStatus.UpdateStatus, so the admin UI/SSE polling sees per-byte progress for distributed installs without any UI-side change. UpgradeBackend is intentionally left silent for now: its wire request (BackendUpgradeRequest) does not carry OpID, and rolling-update fallback is the rarer path. Will be picked up in a follow-up if the worker upgrade path also gets a progress channel. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): InstallBackend tolerates silent (pre-Phase-2) workers A worker on pre-Phase-2 code never publishes progress events. The new master subscribes optimistically; this spec pins that a silent worker still produces a green install with no progressCb ticks. The install reply is the source of truth for terminal state; the progress stream is a best-effort UX enrichment. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document install progress streaming Note the new nodes.<nodeID>.backend.install.<opID>.progress subject and the silent-worker compatibility behavior so operators know to expect real-time progress and what happens on a mixed-version cluster. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): note progress-event ordering trade-off in InstallBackend Document near the goroutine dispatch why ordering at the consumer is best-effort, why it rarely matters in practice (worker debounce >> goroutine jitter), and what a future hardening pass would look like (Seq field + stale-by-seq drop). Stops the next reader from accidentally "fixing" the goroutine pool away. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): add NodeProgress + OpStatus.Nodes for per-node breakdown Adds the data model the UI needs to render an expandable per-node breakdown of a fanned-out backend install. NodeProgress carries node identity (ID + name), per-node status (queued / running_on_worker / success / error / downloading), the current file + bytes + percentage from the Phase 2 progress stream, and any per-node error. OpStatus.Nodes is the slice the /api/operations handler will surface in a follow-up. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): UpdateNodeProgress merges per-node ticks by NodeID GalleryService.UpdateNodeProgress(opID, nodeID, np) merges a NodeProgress into OpStatus.Nodes (keyed by NodeID, no duplicates) and mirrors the latest tick into the aggregate Progress / FileName / DownloadedFileSize / TotalFileSize fields so the legacy single-bar OperationsBar view keeps working unchanged alongside the new per-node breakdown. Concurrent-safe via the existing g.Mutex. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): write per-node OpStatus entries during install fan-out DistributedBackendManager now accepts a nodeProgressSink and feeds it two streams: 1. enqueueAndDrainBackendOp emits a per-node terminal entry on each status it appends to BackendOpResult (queued, success, error, running_on_worker). The opID is threaded through the function so the sink gets the right gallery op identity. 2. The install apply closure fans each BackendInstallProgressEvent into the sink as a downloading entry, alongside the legacy progressCb path so the aggregate single-bar view stays correct. Production wiring passes the GalleryService (which implements UpdateNodeProgress via Task 2) as the sink. Single-node tests pass nil. DeleteBackend and UpgradeBackend pass an empty opID so the sink path no-ops for ops that aren't gallery-tracked the same way as Install. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(operations): expose per-node breakdown on /api/operations When an operation's OpStatus has Nodes entries (populated by the Phase 4 progress sink wiring), surface them as a "nodes" array on the /api/operations response, sorted by node_name for stable rendering. Backward compatible: legacy clients ignore the field; ops without any node entries (single-node mode, model installs) omit the array entirely thanks to the empty-slice guard. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): per-node breakdown in OperationsBar When an install op fans out to more than one worker, the operations bar now shows a "N nodes" chevron that expands into a per-node list. Each row carries the node's status (color-coded pill), the current file being downloaded, byte counts, percentage, and a thin per-node progress bar. Yellow "Worker busy" pill marks running_on_worker status with a tooltip explaining the NATS round-trip timed out but the worker is still installing in the background. Backward compatible: ops without a nodes field (legacy or single-node mode) render as before. State for expand/collapse is local to the component, keyed by jobID/id - reload starts collapsed. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document per-node breakdown in the operations bar Adds a short subsection covering the expandable "N nodes" chevron in the OperationsBar admin UI, the meaning of each status pill, and how it relates to the /api/operations nodes array. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(galleryop): UpdateStatus preserves Nodes when caller sends none Real-world bug surfaced by the Phase 4 multi-worker smoke test: the nodes[] array in /api/operations flickered between a single node at a time on a 2-worker install. Root cause: the Phase 2 progress bridge also calls the legacy progressCb -> UpdateStatus(&OpStatus{...}) on every tick. UpdateStatus then overwrote the entire status pointer, wiping the Nodes slice that UpdateNodeProgress had just merged in. Fix: in UpdateStatus, if the incoming op has an empty Nodes slice, carry forward the previous status's Nodes before storing. Callers that explicitly populate Nodes still win (their slice replaces the prior one, no merge across the two code paths). Two regression specs added pinning both directions of the contract. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): strip implementation details from user-facing docs Trim the new install/upgrade timeout rows and the install-progress sections to focus on what the operator sees and tunes. Drops: - the NATS subject names and pub/sub mechanics - "round-trip" / reconciler / backend.list jargon - /api/operations polling cadence - "pre-2026-05-22" version references Reframes the breakdown text around the admin UI (Operations Bar, chevron, status pills, "Worker busy" tooltip). Implementation context lives in the agent notes and code comments. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(config): move DistributedConfig.Validate flag names to constants The negative-duration check map was a wall of literal kebab-case strings that had to stay in sync with the kong-derived CLI flag names manually. Move them to a Flag* const block alongside the existing Default* block so a rename of either the Go field or the CLI naming convention forces a compile error rather than silent drift. Sole consumer today is Validate; the constants are exported so future operator-facing surfaces (e.g. error messages on other validation paths) can reference them by name instead of repeating the literals. Tests pin both the literal values (so a future "let's just rename this" doesn't accidentally regress the CLI flag) and the negative- duration error message for the new BackendInstall / BackendUpgrade fields. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(distributed): extract NodeStatus and Phase enums to constants Sweep for the same literal-string-as-identifier pattern called out on the Validate flag names: the per-node install status enum ("queued" | "downloading" | "running_on_worker" | "success" | "error") appeared as raw literals across managers_distributed.go (10+ sites, including 3 separate `n.Status == "running_on_worker"` checks), operation.go, and the test suite. Same shape for the Phase enum ("resolving" | "downloading" | "extracting" | "starting") in the worker-side progress publisher. Promote both to exported const blocks: - galleryop.NodeStatus{Queued,Downloading,RunningOnWorker,Success,Error} shared between galleryop.NodeProgress.Status (the wire field) and nodes.NodeOpStatus.Status (the in-process per-node summary) - messaging.Phase{Resolving,Downloading,Extracting,Starting} shared between the worker publisher and any future consumer that needs to switch on phase Tests pin both the literal values (so a future "let's just rename" doesn't silently change the JSON wire) and use the constants in setup (so the producer side stays drift-protected). Wire-format assertions on the /api/operations JSON output keep their literals deliberately, so the constant value can never silently diverge from what the UI receives. Out of scope for this PR (separate cleanup): the finetune and quantization job-status enums have the same anti-pattern with 14+ literal sites each, but predate this PR's work. 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
|
e5d7b84216 |
fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)
* feat(messaging): add backend.upgrade NATS subject + payload types
Splits the slow force-reinstall path off backend.install so it can run on
its own subscription goroutine, eliminating head-of-line blocking between
routine model loads and full gallery upgrades.
Wire-level Force flag on BackendInstallRequest is kept for one release as
the rolling-update fallback target; doc note marks it deprecated.
Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed/worker): add per-backend mutex helper to backendSupervisor
Different backend names lock independently; same backend serializes. This
is the synchronization primitive used by the upcoming concurrent install
handler — without it, wrapping the NATS callback in a goroutine would
race the gallery directory when two requests target the same backend.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(distributed/worker): run backend.install handler in a goroutine
NATS subscriptions deliver messages serially on a single per-subscription
goroutine. With a synchronous install handler, a multi-minute gallery
download would head-of-line-block every other install request to the
same worker — manifesting upstream as a 5-minute "nats: timeout" on
unrelated routine model loads.
The body now runs in its own goroutine, with a per-backend mutex
(lockBackend) protecting the gallery directory from concurrent operations
on the same backend. Different backend names install in parallel.
Backward-compat: req.Force=true is still honored here, so an older master
that hasn't been updated to send on backend.upgrade keeps working.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed/worker): subscribe to backend.upgrade as a separate path
Slow force-reinstall now lives on its own NATS subscription, so a
multi-minute gallery pull cannot head-of-line-block the routine
backend.install handler on the same worker. Same per-backend mutex
guards both — concurrent install + upgrade for the same backend
serialize at the gallery directory; different backends are independent.
upgradeBackend stops every live process for the backend, force-installs
from gallery, and re-registers. It does not start a new process — the
next backend.install will spawn one with the freshly-pulled binary.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): add UpgradeBackend on NodeCommandSender; drop Force from InstallBackend
Master now sends to backend.upgrade for force-reinstall, with a
nats.ErrNoResponders fallback to the legacy backend.install Force=true
path so a rolling update with a new master + an old worker still
converges. The Force parameter leaves the public Go API surface
entirely — only the internal fallback sets it on the wire.
InstallBackend timeout drops 5min -> 3min (most replies are sub-second
since the worker short-circuits on already-running or already-installed).
UpgradeBackend timeout is 15min, sized for real-world Jetson-on-WiFi
gallery pulls.
Updates the admin install HTTP endpoint
(core/http/endpoints/localai/nodes.go) to the new signature too.
router_test.go's fakeUnloader does not yet implement the new interface
shape; Task 3.2 will catch it up before the next package-level test run.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(distributed): update fakeUnloader for new NodeCommandSender shape
InstallBackend lost its force bool param (Force is not part of the public
Go API anymore — only the internal upgrade-fallback path sets it on the
wire). UpgradeBackend gained a method. Fake records both call slices and
provides an installHook concurrency seam for upcoming singleflight tests.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(distributed): cover UpgradeBackend's new subject + rolling-update fallback
Task 3.1 changed the master to publish UpgradeBackend on the new
backend.upgrade subject; the existing UpgradeBackend tests scripted the
old install subject and so all 3 began failing as expected. Updates them
to script SubjectNodeBackendUpgrade with BackendUpgradeReply.
Adds two new specs for the rolling-update fallback:
- ErrNoResponders on backend.upgrade triggers a backend.install
Force=true retry on the same node.
- Non-NoResponders errors propagate to the caller unchanged.
scriptedMessagingClient gains scriptNoResponders (real nats sentinel) and
scriptReplyMatching (predicate-matched canned reply, used to assert that
the fallback path actually sets Force=true on the install retry).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(distributed): coalesce concurrent identical backend.install via singleflight
Six simultaneous chat completions for the same not-yet-loaded model were
observed firing six independent NATS install requests, each serializing
through the worker's per-subscription goroutine and amplifying queue
depth. SmartRouter now wraps the NATS round-trip in a singleflight.Group
keyed by (nodeID, backend, modelID, replica): N concurrent identical
loads share one round-trip and one reply.
Distinct (modelID, replica) keys still fire independent calls, so
multi-replica scaling and multi-model fan-out are unaffected.
fakeUnloader gains a sync.Mutex around its recording slices to keep
concurrent test goroutines race-clean.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(e2e/distributed): drop force arg from InstallBackend test calls
Two e2e test call sites still passed the trailing force bool that was
removed from RemoteUnloaderAdapter.InstallBackend in
|
||
|
LocalAI [bot]andEttore Di Giacinto
|
447c186089 |
fix(distributed): make backend upgrade actually re-install on workers (#9708)
* fix(distributed): make backend upgrade actually re-install on workers UpgradeBackend dispatched a vanilla backend.install NATS event to every node hosting the backend. The worker's installBackend short-circuits on "already running for this (model, replica) slot" and returns the existing address — so the gallery install path was skipped, no artifact was re-downloaded, no metadata was written. The frontend's drift detection then re-flagged the same backends every cycle (installedDigest stays empty → mismatch → "Backend upgrade available (new build)") while "Backend upgraded successfully" landed in the logs at the same time. The user-visible symptom: clicking "Upgrade All" silently does nothing and the same N backends sit on the upgrade list forever. Two coupled fixes, one PR: 1. Force flag on backend.install. Add `Force bool` to BackendInstallRequest and thread it through NodeCommandSender -> RemoteUnloaderAdapter. UpgradeBackend (and the reconciler's pending-op drain when retrying an upgrade) sets force=true; routine load events and admin install endpoints keep force=false. On the worker, force=true stops every live process that uses this backend (resolveProcessKeys for peer replicas, plus the exact request processKey), skips the findBackend short-circuit, and passes force=true into gallery.InstallBackendFromGallery so the on-disk artifact is overwritten. After the gallery install completes, startBackend brings up a fresh process at the same processKey on a new port. 2. Liveness check on the fast path. installBackend's "already running" branch read getAddr without verifying the process was alive, so a gRPC backend that died without the supervisor noticing left a stale (key, addr) entry. The reconciler then dialed that address, got ECONNREFUSED, marked the replica failed, retried install — and the supervisor said "already running addr=…" again. Loop forever, exactly what we observed on a node whose llama-cpp process had died but whose supervisor record persisted. Verify s.isRunning(processKey) before trusting getAddr; if the entry is stale, stopBackendExact cleans up and we fall through to a real install. Backwards-compatible: the new Force field is omitempty, older workers ignore it (their default behavior matches force=false). The signature change on NodeCommandSender.InstallBackend is internal-only. Verified: unit tests in core/services/nodes pass (108s suite). The pre-existing core/backend build break (proto regen pending for word-level timestamps) blocks core/cli and core/http/endpoints/localai package tests but is unrelated to this change. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-7 [Claude Code] * test(e2e/distributed): pass force=false to adapter.InstallBackend NodeCommandSender.InstallBackend gained a final force bool in the upgrade-force commit; the e2e distributed lifecycle tests still called the old 8-arg signature and broke compilation. These tests exercise the routine install path (single replica, default behavior), so force=false preserves their existing semantics. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-7 [Claude Code] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Richard Palethorpe
|
969005b2a1 |
feat(gallery): Speed up load times and clean gallery entries (#9211)
* feat: Rework VRAM estimation and use known_usecases in gallery Signed-off-by: Richard Palethorpe <io@richiejp.com> Assisted-by: Claude:claude-opus-4-7[1m] [Claude Code] * chore(gallery): regenerate gallery index and add known_usecases to model entries Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
Ettore Di Giacinto
|
bbcaebc1ef |
feat(concurrency-groups): per-model exclusive groups for backend loading (#9662)
* feat(concurrency-groups): per-model exclusive groups for backend loading Adds `concurrency_groups: [...]` to model YAML configs. Two models that share a group cannot be loaded concurrently on the same node — loading one evicts the others, reusing the existing pinned/busy/retry policy from LRU eviction. Layered design: - Watchdog (pkg/model): per-node correctness floor — on every Load(), evict any loaded model that shares a group with the requested one. Pinned skips surface NeedMore so the loader retries (and ultimately logs a clear warning), instead of silently allowing the rule to be violated. - Distributed scheduler (core/services/nodes): soft anti-affinity hint — scheduleNewModel prefers nodes that don't already host a same-group model, falling back to eviction only if every candidate has a conflict. Composes with NodeSelector at the same point in the candidate pipeline. Per-node, not cluster-wide: VRAM is a node-local resource, and two heavy models running on different nodes is fine. The ConfigLoader is wired into SmartRouter via a small ConcurrencyConflictResolver interface so the nodes package keeps a narrow surface on core/config. Refactors the inner LRU eviction body into a shared collectEvictionsLocked helper and the loader retry loop into retryEnforce(fn, maxRetries, interval), so both LRU and group enforcement share busy/pinned/retry semantics. Closes #9659. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(watchdog): sync pinned + concurrency_groups at startup The startup-time watchdog setup lives in initializeWatchdog (startup.go), not in startWatchdog (watchdog.go). The latter is only invoked from the runtime-settings RestartWatchdog path. As a result, neither SyncPinnedModelsToWatchdog nor SyncModelGroupsToWatchdog ran at boot, so `pinned: true` and `concurrency_groups: [...]` only became effective after a settings-driven watchdog restart. Fix by adding both sync calls to initializeWatchdog. Confirmed end-to-end: loading model A in group "heavy", then C with no group (coexists), then B in group "heavy" now correctly evicts A and leaves [B, C]. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(test): satisfy errcheck on new os.Remove in concurrency_groups spec CI lint runs new-from-merge-base, so the existing pre-existing `defer os.Remove(tmp.Name())` lines are baseline-grandfathered but the one introduced by the concurrency_groups YAML round-trip test is held to errcheck. Wrap the remove in a closure that discards the error. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
170d55c67d |
fix(distributed): honor NodeSelector in cached-replica lookup, stop empty-backend reconciler scaleups (#9652)
* fix(distributed): honor NodeSelector in cached-replica lookup, stop empty-backend reconciler scaleups
Two distinct bugs were causing tight retry loops in the distributed scheduler:
1. FindAndLockNodeWithModel ignored the model's NodeSelector. When a model
was loaded on multiple nodes and only some matched the current selector,
the function returned the lowest-in_flight node — even one the selector
excluded. Route()'s post-check then fell through to scheduleNewModel,
which targeted the matching node where the model was already at
MaxReplicasPerModel capacity. Eviction couldn't help (the only loaded
model on that node was the one being requested, and it was busy), so
every request looped through "evicting LRU" → "all models busy".
Fix: thread an optional candidateNodeIDs filter through
FindAndLockNodeWithModel. Route() resolves the selector once via a new
resolveSelectorCandidates helper and passes the matching IDs to both
the cached-replica lookup and scheduleNewModel. The same helper
replaces the inline selector block in scheduleNewModel.
2. ScheduleAndLoadModel (reconciler scale-up path) fell back to
scheduleNewModel with backendType="" when no replica had ever been
loaded for a model. The worker rejected the resulting backend.install
("backend name is empty") on every reconciler tick (~30s).
Fix: remove the broken fallback. When GetModelLoadInfo has nothing
stored, return a clear error instead of firing a doomed NATS install.
The reconciler's existing scale-up failure log surfaces it once per
tick; the model auto-replicates as soon as Route() serves it once and
stores load info.
Also downgrade the post-LoadModel-failure StopGRPC error to Debug — that
cleanup attempt usually hits "model not found" because LoadModel failed
before registering the process, and the outer "Failed to load model"
error already carries the real reason.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash]
* test(distributed): cover selector-aware FindAndLockNodeWithModel and reconciler scaleup guard
Two regression tests for the bugs fixed in the previous commit:
1. FindAndLockNodeWithModel — registry-level integration tests verify the
candidateNodeIDs filter:
- Returns the included node even when an excluded node has lower
in_flight (the original selector-mismatch loop scenario).
- Returns not-found when the model is loaded only on excluded nodes,
forcing Route() to fall through to a fresh schedule instead of
reusing the excluded replica.
2. ScheduleAndLoadModel — mock-based test verifies the reconciler scale-up
path returns an error and does NOT fire backend.install when no replica
has been loaded yet. fakeUnloader gains an installCalls slice so this
negative assertion is direct.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
Ettore Di Giacinto
|
6b63b47f61 |
feat(distributed): support multiple replicas of one model on the same node (#9583)
* feat(distributed): support multiple replicas of one model on the same node The distributed scheduler implicitly assumed `(node_id, model_name)` was unique, but the schema didn't enforce it and the worker keyed all gRPC processes by model name alone. With `MinReplicas=2` against a single worker, the reconciler "scaled up" every 30s but the registry never advanced past 1 row — the worker re-loaded the model in-place every tick until VRAM fragmented and the gRPC process died. This change introduces multi-replica-per-node as a first-class concept, with capacity-aware scheduling, a circuit breaker, and VRAM soft-reservation. Operators can declare per-node capacity via the worker flag `--max-replicas-per-model` (mirrored as auto-label `node.replica-slots=N`) or override per-node from the UI. * Schema: BackendNode gains MaxReplicasPerModel (default 1) and ReservedVRAM. NodeModel gains ReplicaIndex (composite with node_id + model_name). ModelSchedulingConfig gains UnsatisfiableUntil/Ticks for the reconciler circuit breaker. * Registry: replica_index threaded through SetNodeModel, RemoveNodeModel, IncrementInFlight, DecrementInFlight, TouchNodeModel, GetNodeModel, SetNodeModelLoadInfo and the InFlightTrackingClient. New helpers: CountReplicasOnNode, NextFreeReplicaIndex (with ErrNoFreeSlot), RemoveAllNodeModelReplicas, FindNodesWithFreeSlot, ClusterCapacityForModel, ReserveVRAM/ReleaseVRAM (atomic UPDATE with ErrInsufficientVRAM), and the unsatisfiable-flag CRUD. * Worker: processKey now `<modelID>#<replicaIndex>` so concurrent loads of the same model land on distinct ports. Adds CLI flag --max-replicas-per-model (env LOCALAI_MAX_REPLICAS_PER_MODEL, default 1) and emits the auto-label. * Router: scheduleNewModel filters candidates by free slot, allocates the replica index, and soft-reserves VRAM before installing the backend. evictLRUAndFreeNode now deletes the targeted row by ID instead of all replicas of the model on the node — fixes a latent bug where evicting one replica orphaned its siblings. * Reconciler: caps scale-up at ClusterCapacityForModel so a misconfig (MinReplicas > capacity) doesn't loop forever. After 3 consecutive ticks of capacity==0 it sets UnsatisfiableUntil for a 5m cooldown and emits a warning. ClearAllUnsatisfiable fires from Register, ApproveNode, SetNodeLabel(s), RemoveNodeLabel and UpdateMaxReplicasPerModel so a new node joining or label changes wake the reconciler immediately. scaleDownIdle removes highest-replica-index first to keep slots compact. * Heartbeat resets reserved_vram to 0 — worker is the source of truth for actual free VRAM; the reservation is only for the in-tick race window between two scheduling decisions. * Probe path (reconciler.probeLoadedModels and health.doCheckAll) now pass the row's replica_index to RemoveNodeModel so an unreachable replica doesn't orphan healthy siblings. * Admin override: PUT /api/nodes/:id/max-replicas-per-model sets a sticky override (preserved across worker re-registration). DELETE clears the override so the worker's flag applies again on next register. Required because Kong defaults the worker flag to 1, so every worker restart would have silently reverted the UI value. * React UI: always-visible slot badge on the node row (muted at default 1, accented when >1); inline editor in the expanded drawer with pencil-to-edit, Save/Cancel, Esc/Enter, "(override)" indicator when the value is admin-set, and a "Reset" button to hand control back to the worker. Soft confirm when shrinking the cap below the count of loaded replicas. Scheduling rules table gets an "Unsatisfiable until HH:MM" status badge surfacing the cooldown. * node.replica-slots filtered out of the labels strip on the row to avoid duplicating the slot badge. 23 new Ginkgo specs (registry, reconciler, inflight, health) cover: multi-replica row independence, RemoveNodeModel of one replica preserving siblings, NextFreeReplicaIndex slot allocation including ErrNoFreeSlot, capacity-gated scale-up with circuit breaker tripping and recovery on Register, scheduleDownIdle ordering, ClusterCapacity math, ReserveVRAM admission gating, Heartbeat reset, override survival across worker re-registration, and ResetMaxReplicasPerModel handing control back. Plus 8 stdlib tests for the worker processKey / CLI / auto-label. Closes the flap reproduced on Qwen3.6-35B against the nvidia-thor worker (single 128 GiB node, MinReplicas=2): the reconciler now caps the scale-up at the cluster's actual capacity instead of looping. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Read] [Edit] [Bash] [Skill:critique] [Skill:audit] [Skill:polish] [Skill:golang-testing] * refactor(react-ui/nodes): tighten capacity editor copy + adopt ActionMenu for row actions * Capacity editor hint trimmed from operator-doc-style ("Sourced from the worker's `--max-replicas-per-model` flag. Changing it here makes it a sticky admin override that survives worker restarts." → "Saved values stick across worker restarts.") and the override-state copy similarly compressed. The full mechanic is no longer needed in the UI — the override pill carries the meaning and the docs cover the rest. * Node row actions migrated from an inline cluster of icon buttons (Drain / Resume / Trash) to the kebab ActionMenu used by /manage for per-row model actions, so dense Nodes tables stay clean. Approve stays as a prominent primary button — it's a stateful admission gate, not a routine action, and elevating it matches how /manage surfaces install-time decisions outside the menu. * The expanded drawer's Labels section now filters node.replica-slots out of the editable label list. The label is owned by the Capacity editor above; surfacing it again as an editable label invited confusion (the Capacity save would clobber any direct edit). Both backend and agent workers benefit — they share the row rendering path, so the action menu and label filter apply to both. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] [chrome-devtools-mcp] [Skill:critique] [Skill:audit] [Skill:polish] * fix(react-ui/nodes): suppress slot badge on agent workers Agent workers don't load models, so the per-node replica capacity is inapplicable to them. Showing "1× slots" on agent rows was a tiny inconsistency from the unified rendering path — gate the badge on node_type !== 'agent' so it only appears on backend workers. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] [chrome-devtools-mcp] * refactor(react-ui/nodes): distill expanded drawer + restyle scheduling form The expanded node drawer used to stack five panels — slot badge, filled capacity box, Loaded Models h4+empty-state, Installed Backends h4+empty-state, Labels h4+chips+form — making routine inspections feel like a control panel. The scheduling rule form wrapped its mode toggle as two 50%-width filled buttons that competed visually with the actual primary action. * Drawer: collapse three rarely-touched config zones (Capacity, Backends, Labels) into one `<details>` "Manage" disclosure (closed by default) with small uppercase eyebrow labels for each zone instead of parallel h4 sub-headings. Loaded Models stays as the at-a-glance headline with a single-line empty hint instead of a boxed empty state. CapacityEditor renders flat (no filled background) — the Manage disclosure provides framing. * Scheduling form: replace the chunky 50%-width button-tabs with the project's existing `.segmented` control (icon + label, sized to content). Mode hint becomes a single tied line below. Fields stack vertically with helper text under inputs and a hairline divider above the right-aligned Save / Cancel. The empty drawer collapses from ~5 stacked sections (~280px tall) to two lines (~80px). The scheduling form now reads as a designed dialog instead of raw building blocks. Both surfaces now match the typographic density and weight of the rest of the admin pages. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] [chrome-devtools-mcp] [Skill:distill] [Skill:audit] [Skill:polish] * feat(react-ui/nodes): replace scheduling form's model picker with searchable combobox The native <select> made operators scroll through every gallery entry to find a model name. The project already has SearchableModelSelect (used in Studio/Talk/etc.) which combines free-text search with the gallery list and accepts typed model names that aren't installed yet — useful for pre-staging a scheduling rule before the node it'll run on has finished bootstrapping. Also drops the now-unused useModels import (the combobox manages the gallery hook internally). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] * refactor(react-ui/nodes): consolidate key/value chip editor + add replica preset chips The Nodes page was rendering the same key=value chip pattern in two places with subtly different markup: the Labels editor in the expanded drawer and (post-distill) the Node Selector input in the scheduling form. The form's input was also a comma-separated string that operators were getting wrong. * Extract <KeyValueChips> as a fully controlled chip-builder. Parent owns the map and decides what onAdd/onRemove does — form state for the scheduling form, API calls for the live drawer Labels editor. Same visuals everywhere; one component to change when polish needs apply. * Replace the comma-separated Node Selector text input with KeyValueChips. Operators were copying syntax from docs and missing commas; the chip vocabulary makes the key=value structure self-documenting. * Add <ReplicaInput>: numeric input + quick-pick preset chips for Min/Max replicas. Picked over a slider because replica counts are exact specs derived from VRAM math (operator decision, not a fuzzy estimate). The chips give one-click access to common values (1/2/3/4 for Min, 0=no-limit/2/4/8 for Max) without the slider's special-value problem (MaxReplicas=0 is categorical, not a position on a continuum). * Drop the now-unused labelInputs state in the Nodes page (the inline label editor's per-node draft state lived there and is now owned by KeyValueChips). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] [Skill:distill] * test: fix CI fallout from multi-replica refactor (e2e/distributed + playwright) Two breakages caught by CI that didn't surface in the local run: * tests/e2e/distributed/*.go — multiple files used the pre-PR2 registry signatures for SetNodeModel / IncrementInFlight / DecrementInFlight / RemoveNodeModel / TouchNodeModel / GetNodeModel / SetNodeModelLoadInfo and one stale adapter.InstallBackend call in node_lifecycle_test.go. All updated to pass replicaIndex=0 — these tests don't exercise multi-replica behavior, they just need to compile against the new signatures. The chip-builder tests in core/services/nodes/ already cover the multi-replica logic. * core/http/react-ui/e2e/nodes-per-node-backend-actions.spec.js — the drawer's distill refactor moved Backends inside a "Manage" <details> disclosure that's collapsed by default. The test helper expanded the node row but never opened Manage, so the per-node backend table was never in the DOM. Helper now clicks `.node-manage > summary` after expanding the row. All 100 playwright tests pass locally; tests/e2e/distributed compiles clean. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude-code:opus-4-7 [Edit] [Bash] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Russell Sim
|
02bb715c0a |
fix(distributed): pass ExternalURI through NATS backend install (#9446)
When installing a backend with a custom OCI URI in distributed mode, the URI was captured in ManagementOp.ExternalURI by the HTTP handler but never forwarded to workers. BackendInstallRequest had no URI field, so workers fell through to the gallery lookup and failed with "no backend found with name <custom-name>". Add URI/Name/Alias fields to BackendInstallRequest and thread them from ManagementOp through DistributedBackendManager.InstallBackend() and the RemoteUnloaderAdapter. On the worker side, route to InstallExternalBackend when URI is set instead of InstallBackendFromGallery. Update all remaining InstallBackend call sites (UpgradeBackend, reconciler pending-op drain, router auto-install) to pass empty strings for the new params. Assisted-by: Claude Code:claude-sonnet-4-6 Signed-off-by: Russell Sim <rsl@simopolis.xyz> |
||
|
Ettore Di Giacinto
|
39c6b3ed66 |
feat: track files being staged (#9275)
This changeset makes visible when files are being staged, so users are aware that the model "isn't ready yet" for requests. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
154fa000d3 |
fix(autoscaling): extract load model from Route() and use as well when doing autoscale (#9270)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
6b6c136210 |
fix(inflight): count inflight from load model, but release afterwards (#9194)
This should fix the count of 1 in flight always showing in the node list Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
8862e3ce60 |
feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler (#9186)
* always enable parallel requests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: move tests to ginkgo Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(smart router): order by available vram Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
dd3376e0a9 |
chore(workers): improve logging, set header timeouts (#9171)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
59108fbe32 |
feat: add distributed mode (#9124)
* feat: add distributed mode (experimental) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix data races, mutexes, transactions Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix events and tool stream in agent chat Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * use ginkgo Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(cron): compute correctly time boundaries avoiding re-triggering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * enhancements, refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do not flood of healthy checks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do not list obvious backends as text backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * tests fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop redundant healthcheck Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * enhancements, refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |