25 Commits

Include renames

Author	SHA1	Message	Date
Ettore Di Giacinto	db9a0a763a	feat(distributed): carry an agent cancel on the worker's own tunnel ... agent.<name>.cancel was the last family on a message bus, and the only reason an agent worker dialled one. Its subscriber is the worker running the execution, and a worker has no database, so the family could not move to the PostgreSQL fan-out carrier: a cancel published there would reach no worker while reporting that it had been sent. It is a control verb now. An agent worker mounts workerctl.PathAgentCancel on the loopback control plane behind its tunnel and applies the cancel to the same registry the executor registers a run on. The frontend issues it through nodes.AgentControlClient.CancelAgentRun. That call is a FAN-OUT and not a pick, because nothing records which worker holds a given execution: the claim row names the claiming replica, and it is deleted when the run ends. Every agent worker a live replica can reach is asked over its own tunnel, relayed by the peer mesh when a peer holds it, and each worker answers only for itself. The answers stay apart, which is why this family was held back. A cancel a worker made is nil. A cancel some worker could not be asked is ErrAgentCancelUndelivered, which is neither a refusal nor a missing run. A cancel every reachable worker declined to own is ErrAgentRunNotOnAnyWorker. A deployment with no agent worker is ErrNoAgentWorker. Neither new sentinel wraps ErrWorkerUnroutable and neither is a worker answer, so nothing is reaped, demoted or evicted because of a cancel. A worker in the ABSENT CONNECTION condition, one whose tunnel was lost inside the reconnect grace, counts as undelivered. It is not retried in the call and not queued: a retry would spend a budget the caller did not choose, and a queue would need durable state whose only consumer is a run whose control stream went with the tunnel. A worker whose departure has outlived the grace is the one routing fact a caller may act on and is excluded, or a single retired agent node would make every cancel undelivered for ever. The fan-out reads a different node set from the pick. A draining worker takes no new work but is still finishing what it holds, so it is offered the cancel; a pending one is refused by the tunnel route on every dial and is not. With that, nothing in LocalAI connects to NATS. The agent worker's dial, its credential ladder and its refresh loop are gone, and so is the frontend's cancel carrier. LOCALAI_NATS_URL is accepted and ignored everywhere, and distributed mode no longer requires it. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:35 +00:00
Ettore Di Giacinto	12571d22d9	feat(distributed): give agent workers a tunnel of their own ... Phase 2 gated agent nodes out of tunnel credentials at the mint site. That was right while nothing dialled into an agent worker: a credential would have replaced nothing, and the gate was structural rather than a second check that could drift. It is wrong now that the frontend needs to reach an agent worker by RPC. attachTunnelToken mints for backend and agent nodes and CLEARS for anything else, through one tunnelEligible predicate rather than two conditions that can be widened separately. ConnectHandler still never reads NodeType, so an empty hash is still what refuses an ineligible node. An agent worker now starts a loopback control server behind the same bearer check a backend worker uses, and holds one tunnel whose only stream tag is http: it runs no backend processes, so the grpc tag has nothing to route to and is not offered. Its MCP tool, MCP discovery and backend.stop verbs are served from ONE implementation reached by both the bus and the tunnel, so a frontend cannot get different bytes depending on which carrier delivered. The tunnel is an ADDITION. --nats-url is still required, and agent jobs, MCP execution, MCP CI jobs and nodes.<id>.backend.stop all still travel on the bus. Absence semantics are unchanged. An agent node now has a real node_connections row whose departure ages past the grace, so the node type check in HealthMonitor.tunnelDeparted stopped being an optimisation and became the rule; its comment says so, and the spec that pins it is shown red under a mutation that deletes the check. The scheduler needed no change: every placement query already filters node_type = backend, so an agent node never reaches nodeMayTakeWork. Shared rules moved to one site each. The request bounds, the POST-only check and the unknown-path 404 live in workerctl and are called by both worker packages; the bearer check that guards every extra route is one function in core/services/nodes used by both server constructors. workerctl.AllPaths splits into BackendPaths and AgentPaths, with AllPaths as their deduped union, because a backend worker does not mount the agent verbs and asserting otherwise would fail a correct worker. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	f86f34c4a1	test(distributed): pin the no-demotion rule at every call site it is stated ... Review fix round 1. Two blocking findings and seven non-blocking; both blocking ones are M12's shape again, and this time on the invariant itself. No production behaviour changes here: everything below was already correct and merely unpinned, so re-inserting the defect left all 679 specs green. The only non-comment edits are one struct-field comment and one log message. "A failed control RPC no longer demotes a node" is stated three times in this package and was pinned once, at ListBackends. Putting MarkUnhealthy back at either op-drain site passed. What that buys in production is the fleet-wide eviction this phase exists to prevent: MarkUnhealthy removes a node from ListDuePendingBackendOps AND from scheduling, so a frontend replica that has just lost its tunnels demotes every node it holds an op for, for a reason that is about the frontend. The reconciler's is the worse of the two, being a background loop nobody is watching. Both now have a spec, each with the recorded op failure as its negative control so "still healthy" cannot pass by nothing having happened. The sweep the review asked for found four more rules stated at more call sites than they were pinned at, and two the review had not: The still-installing surfacing at the manager layer has two call sites and was pinned at InstallBackend. Dropping it from UpgradeBackend reported a spent budget as GREEN SUCCESS: the admin sees the upgrade finished while the worker is still re-pulling gigabytes. The agent-node skip has two call sites and was pinned at ListBackends. Without it the fan-out enqueues a row for every agent node, and an agent worker serves no control plane, so that row can never drain: it retries until the dead-letter cap. The still-installing conversion has three call sites and was pinned at two; the legacy force-install fallback was the gap. Its budget was unpinned too, so the new spec asserts both, on the upgrade budget rather than the install one, since the fallback re-fires an install as part of an upgrade. The carrier split has two call sites and was pinned at one. Hardcoding NodeTypeBackend in UnloadRemoteModelContext passed, and an agent node holding a node_models row would then have its stop sent over a tunnel it does not hold, fail, and leave the row behind. The new spec unloads a model held by one node of each kind and asserts each stop went to that node's own carrier and to no other. router_nats_liveness_test.go asserted demote-on-absence, which production can no longer produce, and its header described the pre-cutover world. The exclusion is unreachable by construction rather than by argument: cluster, the package supplying every control-path dial error, does not link nats.go at all. The file now says that, and gains the assertion that IS load-bearing, a table naming each sentinel a control RPC can answer with and requiring that none of them excludes. Widening the exclusion to ErrWorkerUnroutable reddens four of its entries plus the real-adapter scheduling spec. unroutable keeps no budget-first guard and the reason is now written at it: unlike controlFailure it reads one already-recorded error rather than racing a live deadline, and an expiry is not in streamRefusals, so it falls to the umbrella without one. The two implement the same split at two layers and each now names the other. Fourteen comments still described the bus. Among them the reconciler saying a drain would "churn NATS every tick", a spec comment naming a subject builder this branch deleted, and the agent-skip comment explaining the skip by a subscription that no longer exists. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	615eab5494	feat(distributed): call the worker's control routes instead of the bus ... The ten backend and model lifecycle verbs stop being NATS requests and become HTTP calls on the worker's own control routes, reached through that worker's tunnel on the `http` stream tag that already carries file staging. Nine subject builders and the per-op install-progress subject are deleted with their entries in the worker's NATS permissions; the request and reply DTOs are untouched, so a body on the wire is byte for byte what the subject carried. This closes the merge gate Task 3 left open, which was worse than lost commands. Once the worker stopped subscribing, PingNode was still asking nodes.<id>.backend.list and nodes.<id>.models.running, so EVERY healthy worker answered no-responders, nodeAnswersOnBus read it as absence and pickReachableNode demoted it on the scheduling path. PingNode is a control RPC now, and no control RPC can produce ErrNoResponders, which is the only error that exclusion acts on. Two specs drive pickReachableNode against a real adapter and a worker answering over its control plane, which is the only arrangement that can see the difference: the router's own double never touches a transport and stayed green for the whole window the defect was live. How a control RPC FAILS is the whole of this change, so it is decided in ONE function reading ONE table. A worker's answer passes through unwrapped, so cluster.IsWorkerAnswer still sees it and a reap guard may act on it; everything else is wrapped in ErrWorkerUnroutable so nothing can. There is no third branch, because a third branch is how the eight collapses on this branch happened: each was a site that decided for itself which errors were evidence. A 404 under the prefix is its own sentinel, because it is the worker stating a deployment fact about ITSELF rather than a verdict about a backend, and only the legacy upgrade fallback may act on it. The caller's budget is checked FIRST. A timeout is not a verdict: a refusal arriving in the instant a deadline expires would otherwise be reported as the worker's non-transient answer, which reaps a row, and nothing orders the two timers. A 5xx and an undecodable body are transport failures, not answers. An empty ModelsRunningReply means "this worker is running nothing", which the reconciler acts on, so it must never be manufactured from a body that would not parse. A stream that ends before its reply line is the same rule one layer up: a tunnel dying mid-install is not the worker saying the install failed. backend.stop is split by node type rather than moved. Agent workers hold no tunnel, so they have no control plane to serve, and they still subscribe to nodes.<id>.backend.stop to drop cached MCP sessions; that subject and its agent permission both survive. It is the honest intermediate state until agent workers hold tunnels too. A failed control RPC no longer demotes a node anywhere. ErrNoResponders meant "not on the bus"; a control failure means "this frontend could not route to it", which is equally what a healthy worker re-homing its tunnel between replicas produces. Absence is a fact read from the database, and the scheduler starts reading it in a later task. The rolling-update fallback re-fires a DESTRUCTIVE force-reinstall, so it runs only on the worker's own 404. Its negative direction was pinned at the admin call site and unpinned at the reconciler's, where widening the condition to any error left all 676 specs green: a background drain nobody is watching would then force-reinstall every queued backend the moment a replica lost its tunnels. Three specs cover it, arranged so the force install IS reachable in the negative case and a fallback that fired would show as a call and a drained row. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	e7797db90b	fix(cluster): stop a late request frame reading as the worker's verdict ... Making a worker's refusal reaping evidence created a defect one layer along, at the producer. The worker refused a ReadStreamRequest failure with ErrStreamRequestInvalid and its own comment said "Includes the deadline above expiring", which was harmless while every refusal reached the frontend as "no route" and became a reap the moment one of them did not. So a request frame that had merely not ARRIVED yet was reported as a non-transient verdict about a backend. It is reachable on the relay path, which carries most production traffic: the worker's header timer starts when the OWNING replica opens the stream, while the frame is written by the DIALLING replica only after the relay's acceptance travels back to it, so a whole peer-link round trip runs inside that window, on a link this design deliberately loads with multi-gigabyte artifacts beside token streams. For a long-deadline caller the endpoint is ConnectionEvictingClient, which stops the model across the fleet. It also falsified the "neither clears on its own" argument that licensed the reap. There is now a fourth refusal, ErrStreamNotServed, for what a worker could not serve for a reason of its OWN. It is deliberately outside IsWorkerAnswer, so it reaches a consumer under the no-route umbrella and reaps nothing, which is the same treatment an unrecognised code already gets. Four producers move onto it: a request frame that timed out (a malformed one stays a verdict, because that is a frontend bug no retry fixes), both SetReadDeadline failures, which are facts about the stream and not about a target nothing has dialled yet, and WriteStreamRefusal's default for a reason nobody classified. classifyServiceFailure keeps ErrStreamTargetUnavailable as its default on purpose: inverting it would make errno enumeration the single point of failure for the reap, and a miss there is a row nothing can ever delete. What it gains is a deny-list of two causes that are provably this worker's own clock or its own context. Also: - The read-site caller-deadline guard in the handshake was unpinned: the existing seam spends the budget before the handshake starts, so only the write could ever fail. A spec whose deadline falls between the request and the reply pins it, and each guard now reddens on its own. - The documented worker-first failure line omitted the JSON error envelope the old frontend returns, so an operator grepping it found nothing. - The peer-link disclosure names the aimable per-session receive window in all four places, and LastDialErrorOf records why a third consumer must go through IsWorkerAnswer rather than roll its own list. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	5759b4584b	fix(distributed): let a worker's own refusal be evidence about its backend ... A worker that refuses a stream has answered, and cluster.Dial keeps the three tunnelproto sentinels out of the ErrNoRoute umbrella precisely so a consumer can act on that. No consumer did. Since workers stopped listening, a backend process that crashed on a healthy worker is no longer a dead listener's codes.Unavailable: the worker refuses the stream with ErrStreamTargetUnavailable, gRPC flattens it into Unavailable anyway, and nodes.unroutable reported the whole thing as "this frontend has no route". Every reap path then answered ProbeUnknown and left the row, so the replica slot never freed and at the default MaxReplicasPerModel=1 the only cleanup left was LRU eviction of models that were working. isWorkerAnswer is exported as cluster.IsWorkerAnswer, so the errors the dialer keeps out of the umbrella are by construction the errors the consumers treat as the worker answering. nodes.unroutable and pkg/model's transportFailure both use it; ConnectionEvictingClient, the site reached during inference, goes through transportFailure rather than asking the transport directly. A reply code this frontend does not recognise is still not an answer, so a newer worker's vocabulary costs a retry and not a replica. The reap guards keep the allow-list rather than requiring ErrNoRoute: an unrecognised dial error must mean "no route", never "the backend is gone". Also in this final pass over the branch: - Docs: recommend upgrading FRONTENDS first, with the symptom of each order. Workers-first fails now that a 4xx registration is a verdict rather than an outage, so an old frontend's "address is required for backend workers" makes each restarted worker exit and drains the fleet a node per restart. - Docs: LOCALAI_WORKER_TUNNEL=false is a fatal startup error, not a degraded mode, in both places that described it; and a frontend rollback needs every worker restarted, because re-registration force-clears the address columns. - A replica with no advertised address now says so every five minutes and names the workers only it can reach, instead of one startup warning for a cost paid for the life of the process. - callerRanOut's rule now holds at all three siblings, so an expired caller deadline stops reading as a broken tunnel; probeHealth's withdrawn reason for using the raw client is corrected; the dead DoOrCached is deleted and its coverage kept on DoOrCachedResult; sweepLeakedInFlight enumerates the outcomes that reach it. - The peer route's self-declared id is recorded as a phase-3 deferral, in the handler, in the isolation claim it narrows, and in the operator docs. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	34f9b14b67	fix(grpc): let the transport answer through the wrappers, not only past gRPC ... Re-review round 2. One blocking defect, and it was the concern I filed myself last round and mis-scoped as a future trap. It was live, and it sat on the most destructive reaping path of the five. RouteResult.Client is an InFlightTrackingClient, over a FileStagingClient when a stager is configured. model_router puts that on the cached remote model and pkg/model's checkIsLoaded asks IT whether the transport failed. Both wrappers embed grpc.Backend, which does not declare LastDialError, so the type assertion read nil and the guard added last round fell straight through to the old eviction. That eviction sends backend.stop over NATS to every node holding the model and deletes every replica row, where the other sites delete one. The spec covering it built a bare client by hand, which is why it passed while production did not. This is the third time in this task a correct fix was disarmed one layer out, so the fix is a mechanism rather than two methods. BackendUnwrapper is one line per decorator, LastDialErrorOf walks the chain, and both consumers now call it instead of each keeping its own assertion. One implementation, no per-caller policy to get wrong. Sweeping every type that embeds or holds a grpc.Backend found a third decorator the review had not named, and it is itself a reaping consumer of the same collapsed signal. ConnectionEvictingClient is built for remote models in initializers.go and its evict callback runs ShutdownModel; it fires during INFERENCE rather than on a health check, so a tunnel blip mid-request was enough to stop a model that was loaded and serving. It consults the transport first now. A locally spawned backend has no custom transport, so that path is unchanged byte for byte. Everything else touching a Backend is a consumer rather than a decorator; there is no fourth. The probe cache joiner shape is pinned. It was the right design last round with nothing holding it: the mutation back to a closed-over variable passed all 602 specs in the package. Eight goroutines coalesced on a probe that blocks on a channel now assert every joiner gets the leader's REASON and not just its answer, which is the difference between a leader declining to reap and its seven joiners reaping on the leader's own observation. The LastDialError scope note claimed an exactness it does not have at checkIsLoaded, which reads a shared long-lived client after releasing opMutex. It now says which caller is not exact, why the imprecision is accepted there, and what making it exact would cost. The four-outcome table in the docs still said a worker with no live owner is treated as absent and rescheduled, contradicting the code and the paragraph nine lines below it. None of those outcomes is absence any more, and the table says so, names the fifth, and points at the heartbeat as the thing that does decide presence. Five mutations, each reddening named specs, including the two the reviewer found surviving. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	ed16aa2fd2	fix(cluster): make "no route" a condition of its own, and let it out of the package ... Review round 1 on task 6. Five blocking findings, all with the same root: the conditions the dialer kept apart were erased one layer out, because every one of them arrived at core/services/nodes as a gRPC codes.Unavailable, which is also what a backend process that died produces. Four call sites acted on that by deleting a replica row, one of them after a single failed probe. The fifth condition is ErrNoRoute: this replica could not get a request to a worker's backend, and no claim at all about the worker. A worker's presence is its HEARTBEAT, which nodes owns; a route is a separate fact that cluster owns, and the two now differ. They differ in normal operation, not exotically: a worker that has not dialled its tunnel yet after a frontend-first upgrade is unroutable on every request while it heartbeats and serves. Two properties, both mutation-tested. Every failure to resolve or open a route carries ErrNoRoute, so a consumer has one check to make. No failure carries an absence sentinel: routeFailure is the single place that rule lives, and it keeps ErrNoConnection and ErrInstanceNotFound in the message and out of the unwrap chain, the guarantee unreachableError already made for peers. Everything else stays matchable, so ErrNotOwner and ErrPeerUnreachable are unchanged for anyone who can act on them. A worker's own refusal carries no umbrella, because a worker that answers has demonstrated it is there and that is the only real evidence on the path. Crossing the boundary needed a value, not a code. NewClientWithDialer wraps the dialer and records each outcome; LastDialError hands it back behind a narrow interface, and nodes.unroutable turns it into ErrWorkerUnroutable with the cluster sentinels still in the chain. A spec asserts a dial failing with ErrNoRoute plus ErrPeerUnreachable arrives matching all three and matching neither absence sentinel. The sweep found a fourth site the review had not named: pkg/model checkIsLoaded evicts a remote model on a connection error, and a tunnel dial failure is one. Four other reap sites were cleared with reasons - inflight and the worker authoritative pass reap only on semantic answers, scale-down is driven by last_used, abandoned loads decide on the node's heartbeat. Every fixed site also grew the opposite spec, so the new check cannot pass by never reaping. probeCache carries the reason through singleflight rather than a closed-over variable. A variable is only written by the goroutine that runs the probe, so the leader would correctly decline to reap while every joiner reaped on the leader's own observation; a mutation reproduces exactly that. The docs sentence promising LOCALAI_WORKER_TUNNEL=false restores direct dialling is gone. There is no such path, so it said the operator could take a worker dark and call it a rollback. Replaced with the upgrade order that is actually safe. The deadline spec the reviewer found vacuous now waits on the dial context's own Done channel before touching the stream, so the armed deadline has really expired; the mutation that survived for the reviewer reddens it. Nine mutations, each reddening a named spec, including both halves of isAbsenceClaim independently. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
Ettore Di Giacinto	e29a4e5d15	feat(cluster): reach every worker through its tunnel, never its address ... The tunnel, the fence, the registry and the relay were all built and none of them carried a byte: every dial from the frontend still went to the address a worker registered. This is where that stops. One WorkerDialer resolves where a worker's tunnel is held, opens a stream on it locally or relays through the owning replica, and hands back a conn past both handshakes; gRPC, the file stager's HTTP client and the log-streaming WebSocket are all pointed at it. A worker's address stops being somewhere to connect to and becomes the name of which backend process a stream is for. It still appears in URLs, logs and errors, because that is what identifies the process; what it no longer decides is where the bytes go. Nothing falls back to dialling it. BackendClientFactory now has exactly one method, NewClientForNode, and returns an error where there is no way to reach the worker. The direct-dial constructor was removed rather than kept beside it, because leaving one on the interface keeps the bypass one word away from every call site that holds an address, which is all of them. The second construction path is closed too. DistributedModelStore built remote models with a nil client, and pkg/model.Model.GRPC then dialled the raw address lazily on first use - reached in production by ShutdownModel's Free and by the backend monitor's Status. Those models now carry the tunnel-backed client, and a model that cannot be given one is logged and not listed. Four conditions stay unmixable, and one path produces absence: the dialer answers ErrNoConnection only where Owner's liveness join did. A peer that will not answer, a stale ownership row, a worker's own refusal and a missing relay path are each reported as themselves. This matters because nodes ACTS on absence, and the collapse would have it reclaim the models of a worker that is connected and busy. That is not hypothetical. Writing the mutation for it exposed the bug in this change's own first draft: probeHealth returned bare false when it could not build a client, and tryWarmPath deletes the replica row on a false probe. A frontend whose dialer broke would have emptied node_models for the whole deployment while every model kept running. probeHealth now returns alive and probed separately, the reconciler gets a ProbeUnknown outcome that neither advances nor clears a failure streak, and the health monitor skips rather than counting a miss. Task 5 left the relay's open timeout at a fixed 15s and said so: no operator has the information to set it, because the number that matters is the original client's remaining budget, which is invisible on the relay side. The dialer has that budget, so it now states it in the relay request frame and the owner takes the smaller of the two. It can only shorten - a patient client must not be able to park a relay goroutine and a stream slot on a worker that stopped accepting. Zero is written as no budget at all, since on the far side the number zero is a caller with nothing left and would refuse healthy traffic. Seven mutations, each reddening a named spec: peer-unreachable as absence; the local-failure guard dropped; max instead of min on the budget; the nil-client model restored; ProbeUnknown falling through to the reaper; OwnerRow instead of Owner; probed collapsed into alive. The first budget spec passed for the wrong reason - a handshake deadline, not the relay - and was replaced by three that each assert one link, including one where the spec plays the owning replica and reads the budget out of the frame instead of inferring it from a clock. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-20 03:05:34 +00:00
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>	2026-09-11 23:08:26 +00:00
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>	2026-08-29 09:16:50 +02:00
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]	2026-08-23 20:44:43 +00:00
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>	2026-08-22 22:44:03 +02:00
3 people	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>	2026-08-15 13:20:11 +02:00
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>	2026-07-23 00:03:21 +02:00
LocalAI [bot]andEttore Di Giacinto	858257eaf0	fix(distributed): self-heal stale 'model not loaded' routing (#10181) ... * fix(distributed): self-heal stale 'model not loaded' routing In distributed mode the registry can list a model as loaded on a node while the worker has evicted it (autonomous LRU eviction, an out-of-band unload, etc.) yet the backend process survives. The router's cached-node check only verifies the process is alive (probeHealth), so it routes there and inference fails with "<backend>: model not loaded" — and stays broken until the controller restarts and rebuilds its registry. InFlightTrackingClient now reconciles this: when a tracked inference call returns a model-not-loaded error, it drops the stale replica row (RemoveNodeModel) so the next request reloads the model on a healthy node instead of routing back to the evicted one. The original error is returned unchanged; only the registry is corrected. Assisted-by: Claude:claude-opus-4-8 go vet Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(distributed): typed model-not-loaded error via gRPC status code Replace the controller-side error-string match with a shared, code-aware helper. Go error types don't survive the gRPC boundary, so the signal is carried as a status code (FailedPrecondition): - pkg/grpc/grpcerrors: ModelNotLoaded(backend) constructor + IsModelNotLoaded(err) checker (status-code first, message fallback for backends not yet migrated). - InFlightTrackingClient.reconcile now uses grpcerrors.IsModelNotLoaded. - Migrate the Go backends that emit this error (parakeet-cpp, cloud-proxy, rfdetr-cpp) to the typed constructor. Acting on a false positive is harmless (the model is just reloaded). Assisted-by: Claude:claude-opus-4-8 go vet 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>	2026-06-05 09:01:36 +02:00
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>	2026-05-30 23:24:22 +02:00
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>	2026-05-25 13:00:06 +02:00
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>	2026-05-05 08:42:50 +02:00
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>	2026-05-04 09:42:14 +02:00
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>	2026-04-27 21:20:05 +02:00
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>	2026-04-08 08:27:51 +02:00
Ettore Di Giacinto	6c635e8353	feat: add resume endpoint to undrain nodes (#9197) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-04-01 18:21:43 +02:00
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>	2026-03-31 08:28:56 +02:00
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>	2026-03-30 00:47:27 +02:00