mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-01 12:42:55 -04:00
* feat(distributed): add configurable NATS backend install/upgrade timeouts Adds BackendInstallTimeout and BackendUpgradeTimeout to DistributedConfig with 15m defaults, following the existing MCPToolTimeout / WorkerWaitTimeout pattern. These will replace the hardcoded literals in RemoteUnloaderAdapter so admin-driven backend installs across the cluster survive long OCI image pulls that previously timed out at 3m. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(distributed): gofmt alignment after timeout fields Re-aligns the Validate() negative-duration map and the Default* const block so the new BackendInstall/UpgradeTimeout entries do not leave the surrounding columns mis-padded. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(cli): surface LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT and _UPGRADE_TIMEOUT Parses the two new env vars on the run CLI and threads them through the existing AppOption builder so DistributedConfig picks them up. Invalid duration strings now fail loudly at startup rather than silently falling back to the default. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): inject NATS install/upgrade timeouts into RemoteUnloaderAdapter Removes the hardcoded 3m / 15m literals from RemoteUnloaderAdapter and threads in DistributedConfig.BackendInstallTimeoutOrDefault() and BackendUpgradeTimeoutOrDefault() at construction. Install now defaults to 15m (was 3m); cold OCI image pulls on Jetson Wi-Fi routinely blew past the old ceiling. Scripted messaging client captures the timeout so tests can assert the configured value actually reaches the NATS request. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): introduce galleryop.ErrWorkerStillInstalling sentinel When the NATS request-reply for backend.install (or .upgrade) times out the worker is almost always still pulling the OCI image. Wrap the timeout in a typed sentinel so the manager above can distinguish "worker hung" from "worker still working" and leave the pending_backend_ops row in place for the reconciler to confirm via backend.list. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): treat NATS install timeout as in-progress, not failure When a worker times out replying to backend.install but the install is still running on the worker, enqueueAndDrainBackendOp now reports a running_on_worker status and pushes NextRetryAt out by the install timeout so the reconciler does not immediately re-fire another install while the worker is still pulling the image. The pending_backend_ops row stays in place for the next reconciler pass to confirm via backend.list. InstallBackend wraps the result in galleryop.ErrWorkerStillInstalling so callers can branch (galleryop renders yellow in-progress instead of red error). UpgradeBackend uses the same wrap. Adds RemoteUnloaderAdapter.InstallTimeout() so the manager can push NextRetryAt by the configured timeout without reaching into a private field, and NodeRegistry.RecordPendingBackendOpInFlight as the soft cousin of RecordPendingBackendOpFailure. Also includes incidental gofmt-driven struct-field alignment in registry.go on lines unrelated to the change (touched files are re-formatted to canonical form per project policy). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): don't increment Attempts on in-flight install timeout An in-flight timeout (worker still pulling the OCI image) is not a failed attempt, it's a delayed one. Incrementing Attempts let genuinely-progressing slow installs (e.g. 30 GB CUDA images on Wi-Fi) trip the reconciler's maxPendingBackendOpAttempts cap and dead-letter the queue row while the worker was still legitimately working. RecordPendingBackendOpInFlight now only updates LastError and NextRetryAt. Also documents "running_on_worker" in the NodeOpStatus.Status enum comment so Task 6 implementers see the full surface. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): surface ErrWorkerStillInstalling as non-error OpStatus When the distributed backend manager returns an error that wraps ErrWorkerStillInstalling, backendHandler now completes the op with a "still installing in background" message rather than marking it as a red failure. Admin UI sees a yellow in-progress state; reconciler confirms completion on its next pass. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): end-to-end install-timeout-then-reconcile Wires Task 1-6 end-to-end so any seam mismatch surfaces in CI rather than during a real cluster install. NATS times out, the queue row stays alive with running_on_worker status, the worker eventually reports the backend installed via backend.list, the manager surfaces it via ListBackends. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT / _UPGRADE_TIMEOUT Add the two new operator-tunable env vars to the Frontend Configuration table in the distributed-mode docs. Explains the 15m default, when to raise it (slow links pulling multi-GB OCI images), and the new "still installing in background" admin-UI state when the round-trip times out but the worker is still working. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): clear pending install rows when backend.list confirms DistributedBackendManager.ListBackends now proactively clears pending_backend_ops install rows whose (nodeID, backend) is reported installed by backend.list. Operator UI updates immediately instead of waiting up to installTimeout (default 15m) for the next reconciler tick after NextRetryAt. Only install rows are cleared; upgrade and delete intents are not satisfied by presence in backend.list and continue to drain through their normal reconciler paths. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(messaging): add BackendInstallProgressEvent wire type and subject New NATS subject nodes.<nodeID>.backend.install.<opID>.progress lets the worker publish transient progress events (file, current/total bytes, percentage, phase) while a long-running install pulls its OCI image. BackendInstallRequest gains an optional OpID field so the worker knows which subject to publish on. Transient pub/sub (not JetStream): the install reply remains ground truth for success/failure; dropped progress events are tolerable. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(messaging): drop em-dash from BackendInstallProgress test comment Per project convention (no em-dashes anywhere). Comment substance is unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): worker publishes debounced install progress over NATS When BackendInstallRequest.OpID is set, the worker's backend.install handler wires a debounced publisher (250ms window) into the gallery download callback. Each tick becomes a BackendInstallProgressEvent on nodes.<nodeID>.backend.install.<opID>.progress; the publisher always emits a final event on Flush so the UI sees the terminal percentage. Old masters that do not set OpID continue to run silent installs: no behavior change for them. Lock ordering: the publisher releases its mutex before calling messaging.Publish so a slow network never stalls the install loop. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): RemoteUnloaderAdapter subscribes to install progress InstallBackend gains opID + onProgress parameters. When both are set, the adapter subscribes to nodes.<nodeID>.backend.install.<opID>.progress BEFORE publishing the install request, decodes each message into the caller's onProgress callback in a goroutine (so a slow callback never stalls the NATS reader thread), and unsubscribes after RequestJSON returns. When onProgress is nil OR opID is empty (the reconciler retry path), subscription is skipped entirely - silent installs cost nothing extra. Subscribe failure is logged at Warn and the install proceeds without progress streaming; the NATS round-trip still owns terminal status. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): forward backend install progress into galleryop OpStatus DistributedBackendManager.InstallBackend now passes the gallery op ID and a progress bridge into the adapter call. Each BackendInstallProgressEvent from the worker becomes a galleryop.ProgressCallback tick - which the existing backendHandler already turns into OpStatus.UpdateStatus, so the admin UI/SSE polling sees per-byte progress for distributed installs without any UI-side change. UpgradeBackend is intentionally left silent for now: its wire request (BackendUpgradeRequest) does not carry OpID, and rolling-update fallback is the rarer path. Will be picked up in a follow-up if the worker upgrade path also gets a progress channel. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(distributed): InstallBackend tolerates silent (pre-Phase-2) workers A worker on pre-Phase-2 code never publishes progress events. The new master subscribes optimistically; this spec pins that a silent worker still produces a green install with no progressCb ticks. The install reply is the source of truth for terminal state; the progress stream is a best-effort UX enrichment. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document install progress streaming Note the new nodes.<nodeID>.backend.install.<opID>.progress subject and the silent-worker compatibility behavior so operators know to expect real-time progress and what happens on a mixed-version cluster. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): note progress-event ordering trade-off in InstallBackend Document near the goroutine dispatch why ordering at the consumer is best-effort, why it rarely matters in practice (worker debounce >> goroutine jitter), and what a future hardening pass would look like (Seq field + stale-by-seq drop). Stops the next reader from accidentally "fixing" the goroutine pool away. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): add NodeProgress + OpStatus.Nodes for per-node breakdown Adds the data model the UI needs to render an expandable per-node breakdown of a fanned-out backend install. NodeProgress carries node identity (ID + name), per-node status (queued / running_on_worker / success / error / downloading), the current file + bytes + percentage from the Phase 2 progress stream, and any per-node error. OpStatus.Nodes is the slice the /api/operations handler will surface in a follow-up. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(galleryop): UpdateNodeProgress merges per-node ticks by NodeID GalleryService.UpdateNodeProgress(opID, nodeID, np) merges a NodeProgress into OpStatus.Nodes (keyed by NodeID, no duplicates) and mirrors the latest tick into the aggregate Progress / FileName / DownloadedFileSize / TotalFileSize fields so the legacy single-bar OperationsBar view keeps working unchanged alongside the new per-node breakdown. Concurrent-safe via the existing g.Mutex. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(distributed): write per-node OpStatus entries during install fan-out DistributedBackendManager now accepts a nodeProgressSink and feeds it two streams: 1. enqueueAndDrainBackendOp emits a per-node terminal entry on each status it appends to BackendOpResult (queued, success, error, running_on_worker). The opID is threaded through the function so the sink gets the right gallery op identity. 2. The install apply closure fans each BackendInstallProgressEvent into the sink as a downloading entry, alongside the legacy progressCb path so the aggregate single-bar view stays correct. Production wiring passes the GalleryService (which implements UpdateNodeProgress via Task 2) as the sink. Single-node tests pass nil. DeleteBackend and UpgradeBackend pass an empty opID so the sink path no-ops for ops that aren't gallery-tracked the same way as Install. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(operations): expose per-node breakdown on /api/operations When an operation's OpStatus has Nodes entries (populated by the Phase 4 progress sink wiring), surface them as a "nodes" array on the /api/operations response, sorted by node_name for stable rendering. Backward compatible: legacy clients ignore the field; ops without any node entries (single-node mode, model installs) omit the array entirely thanks to the empty-slice guard. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): per-node breakdown in OperationsBar When an install op fans out to more than one worker, the operations bar now shows a "N nodes" chevron that expands into a per-node list. Each row carries the node's status (color-coded pill), the current file being downloaded, byte counts, percentage, and a thin per-node progress bar. Yellow "Worker busy" pill marks running_on_worker status with a tooltip explaining the NATS round-trip timed out but the worker is still installing in the background. Backward compatible: ops without a nodes field (legacy or single-node mode) render as before. State for expand/collapse is local to the component, keyed by jobID/id - reload starts collapsed. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): document per-node breakdown in the operations bar Adds a short subsection covering the expandable "N nodes" chevron in the OperationsBar admin UI, the meaning of each status pill, and how it relates to the /api/operations nodes array. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(galleryop): UpdateStatus preserves Nodes when caller sends none Real-world bug surfaced by the Phase 4 multi-worker smoke test: the nodes[] array in /api/operations flickered between a single node at a time on a 2-worker install. Root cause: the Phase 2 progress bridge also calls the legacy progressCb -> UpdateStatus(&OpStatus{...}) on every tick. UpdateStatus then overwrote the entire status pointer, wiping the Nodes slice that UpdateNodeProgress had just merged in. Fix: in UpdateStatus, if the incoming op has an empty Nodes slice, carry forward the previous status's Nodes before storing. Callers that explicitly populate Nodes still win (their slice replaces the prior one, no merge across the two code paths). Two regression specs added pinning both directions of the contract. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(distributed): strip implementation details from user-facing docs Trim the new install/upgrade timeout rows and the install-progress sections to focus on what the operator sees and tunes. Drops: - the NATS subject names and pub/sub mechanics - "round-trip" / reconciler / backend.list jargon - /api/operations polling cadence - "pre-2026-05-22" version references Reframes the breakdown text around the admin UI (Operations Bar, chevron, status pills, "Worker busy" tooltip). Implementation context lives in the agent notes and code comments. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(config): move DistributedConfig.Validate flag names to constants The negative-duration check map was a wall of literal kebab-case strings that had to stay in sync with the kong-derived CLI flag names manually. Move them to a Flag* const block alongside the existing Default* block so a rename of either the Go field or the CLI naming convention forces a compile error rather than silent drift. Sole consumer today is Validate; the constants are exported so future operator-facing surfaces (e.g. error messages on other validation paths) can reference them by name instead of repeating the literals. Tests pin both the literal values (so a future "let's just rename this" doesn't accidentally regress the CLI flag) and the negative- duration error message for the new BackendInstall / BackendUpgrade fields. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(distributed): extract NodeStatus and Phase enums to constants Sweep for the same literal-string-as-identifier pattern called out on the Validate flag names: the per-node install status enum ("queued" | "downloading" | "running_on_worker" | "success" | "error") appeared as raw literals across managers_distributed.go (10+ sites, including 3 separate `n.Status == "running_on_worker"` checks), operation.go, and the test suite. Same shape for the Phase enum ("resolving" | "downloading" | "extracting" | "starting") in the worker-side progress publisher. Promote both to exported const blocks: - galleryop.NodeStatus{Queued,Downloading,RunningOnWorker,Success,Error} shared between galleryop.NodeProgress.Status (the wire field) and nodes.NodeOpStatus.Status (the in-process per-node summary) - messaging.Phase{Resolving,Downloading,Extracting,Starting} shared between the worker publisher and any future consumer that needs to switch on phase Tests pin both the literal values (so a future "let's just rename" doesn't silently change the JSON wire) and use the constants in setup (so the producer side stays drift-protected). Wire-format assertions on the /api/operations JSON output keep their literals deliberately, so the constant value can never silently diverge from what the UI receives. Out of scope for this PR (separate cleanup): the finetune and quantization job-status enums have the same anti-pattern with 14+ literal sites each, but predate this PR's work. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
1640 lines
50 KiB
Go
1640 lines
50 KiB
Go
package routes
|
|
|
|
import "os"
|
|
|
|
import (
|
|
"cmp"
|
|
"context"
|
|
"fmt"
|
|
"math"
|
|
"net/http"
|
|
"net/url"
|
|
"slices"
|
|
"sort"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/google/uuid"
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/LocalAI/core/application"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/gallery"
|
|
"github.com/mudler/LocalAI/core/http/auth"
|
|
"github.com/mudler/LocalAI/core/http/endpoints/localai"
|
|
"github.com/mudler/LocalAI/core/p2p"
|
|
"github.com/mudler/LocalAI/core/services/galleryop"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
"github.com/mudler/LocalAI/pkg/vram"
|
|
"github.com/mudler/LocalAI/pkg/xsysinfo"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
const (
|
|
nameSortFieldName = "name"
|
|
repositorySortFieldName = "repository"
|
|
licenseSortFieldName = "license"
|
|
statusSortFieldName = "status"
|
|
ascSortOrder = "asc"
|
|
multimodalFilterKey = "multimodal"
|
|
)
|
|
|
|
// usecaseFilters maps UI filter keys to ModelConfigUsecase flags for
|
|
// capability-based gallery filtering.
|
|
var usecaseFilters = map[string]config.ModelConfigUsecase{
|
|
config.UsecaseChat: config.FLAG_CHAT,
|
|
config.UsecaseImage: config.FLAG_IMAGE,
|
|
config.UsecaseVideo: config.FLAG_VIDEO,
|
|
config.UsecaseVision: config.FLAG_VISION,
|
|
config.UsecaseTTS: config.FLAG_TTS,
|
|
config.UsecaseTranscript: config.FLAG_TRANSCRIPT,
|
|
config.UsecaseSoundGeneration: config.FLAG_SOUND_GENERATION,
|
|
config.UsecaseEmbeddings: config.FLAG_EMBEDDINGS,
|
|
config.UsecaseRerank: config.FLAG_RERANK,
|
|
config.UsecaseDetection: config.FLAG_DETECTION,
|
|
config.UsecaseVAD: config.FLAG_VAD,
|
|
config.UsecaseAudioTransform: config.FLAG_AUDIO_TRANSFORM,
|
|
config.UsecaseDiarization: config.FLAG_DIARIZATION,
|
|
config.UsecaseRealtimeAudio: config.FLAG_REALTIME_AUDIO,
|
|
}
|
|
|
|
// extractHFRepo tries to find a HuggingFace repo ID from model overrides or URLs.
|
|
func extractHFRepo(overrides map[string]any, urls []string) string {
|
|
if overrides != nil {
|
|
if params, ok := overrides["parameters"].(map[string]any); ok {
|
|
if modelRef, ok := params["model"].(string); ok {
|
|
if repoID, ok := vram.ExtractHFRepoID(modelRef); ok {
|
|
return repoID
|
|
}
|
|
}
|
|
}
|
|
}
|
|
for _, u := range urls {
|
|
if repoID, ok := vram.ExtractHFRepoID(u); ok {
|
|
return repoID
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
// buildEstimateInput creates a vram.ModelEstimateInput from gallery model metadata.
|
|
func buildEstimateInput(m *gallery.GalleryModel) vram.ModelEstimateInput {
|
|
var input vram.ModelEstimateInput
|
|
input.Size = m.Size
|
|
if hfRepoID := extractHFRepo(m.Overrides, m.URLs); hfRepoID != "" {
|
|
input.HFRepo = hfRepoID
|
|
}
|
|
for _, f := range m.AdditionalFiles {
|
|
if vram.IsWeightFile(f.URI) {
|
|
input.Files = append(input.Files, vram.FileInput{URI: f.URI, Size: 0})
|
|
}
|
|
}
|
|
return input
|
|
}
|
|
|
|
// parseContextSizes parses a comma-separated list of context sizes from a query param.
|
|
// Returns a default of [8192] if the param is empty or unparseable.
|
|
func parseContextSizes(raw string) []uint32 {
|
|
if raw == "" {
|
|
return []uint32{8192}
|
|
}
|
|
var sizes []uint32
|
|
for _, s := range strings.Split(raw, ",") {
|
|
s = strings.TrimSpace(s)
|
|
if v, err := strconv.ParseUint(s, 10, 32); err == nil && v > 0 {
|
|
sizes = append(sizes, uint32(v))
|
|
}
|
|
}
|
|
if len(sizes) == 0 {
|
|
return []uint32{8192}
|
|
}
|
|
return sizes
|
|
}
|
|
|
|
// getDirectorySize calculates the total size of files in a directory
|
|
// metaParentOf returns the name of the auto-resolving (meta) backend that
|
|
// declares `name` as one of its hardware-specific variants in its
|
|
// CapabilitiesMap, or "" if there is no such parent. The install picker uses
|
|
// this to render hints like "CPU build of llama-cpp" without re-walking the
|
|
// whole gallery on the client side.
|
|
func metaParentOf(name string, backends gallery.GalleryElements[*gallery.GalleryBackend]) string {
|
|
for _, b := range backends {
|
|
if !b.IsMeta() {
|
|
continue
|
|
}
|
|
for _, concreteName := range b.CapabilitiesMap {
|
|
if concreteName == name {
|
|
return b.Name
|
|
}
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func getDirectorySize(path string) (int64, error) {
|
|
var totalSize int64
|
|
entries, err := os.ReadDir(path)
|
|
if err != nil {
|
|
return 0, err
|
|
}
|
|
for _, entry := range entries {
|
|
info, err := entry.Info()
|
|
if err != nil {
|
|
continue
|
|
}
|
|
if !info.IsDir() {
|
|
totalSize += info.Size()
|
|
}
|
|
}
|
|
return totalSize, nil
|
|
}
|
|
|
|
// RegisterUIAPIRoutes registers JSON API routes for the web UI
|
|
func RegisterUIAPIRoutes(app *echo.Echo, cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig, galleryService *galleryop.GalleryService, opcache *galleryop.OpCache, applicationInstance *application.Application, adminMiddleware echo.MiddlewareFunc) {
|
|
|
|
// Operations API - Get all current operations (models + backends)
|
|
app.GET("/api/operations", func(c echo.Context) error {
|
|
processingData, taskTypes := opcache.GetStatus()
|
|
|
|
operations := []map[string]any{}
|
|
for galleryID, jobID := range processingData {
|
|
taskType := "installation"
|
|
if tt, ok := taskTypes[galleryID]; ok {
|
|
taskType = tt
|
|
}
|
|
|
|
status := galleryService.GetStatus(jobID)
|
|
progress := 0
|
|
isDeletion := false
|
|
isQueued := false
|
|
isCancelled := false
|
|
isCancellable := false
|
|
message := ""
|
|
|
|
if status != nil {
|
|
// Skip successfully completed operations
|
|
if status.Processed && !status.Cancelled && status.Error == nil {
|
|
continue
|
|
}
|
|
// Skip cancelled operations that are processed (they're done, no need to show)
|
|
if status.Processed && status.Cancelled {
|
|
continue
|
|
}
|
|
|
|
progress = int(status.Progress)
|
|
isDeletion = status.Deletion
|
|
isCancelled = status.Cancelled
|
|
isCancellable = status.Cancellable
|
|
message = status.Message
|
|
if isDeletion {
|
|
taskType = "deletion"
|
|
}
|
|
if isCancelled {
|
|
taskType = "cancelled"
|
|
}
|
|
} else {
|
|
// Job is queued but hasn't started
|
|
isQueued = true
|
|
isCancellable = true
|
|
message = "Operation queued"
|
|
}
|
|
|
|
// Determine if it's a model or backend
|
|
// First check if it was explicitly marked as a backend operation
|
|
isBackend := opcache.IsBackendOp(galleryID)
|
|
// If not explicitly marked, check if it matches a known backend from the gallery
|
|
if !isBackend {
|
|
backends, _ := gallery.AvailableBackends(appConfig.BackendGalleries, appConfig.SystemState)
|
|
for _, b := range backends {
|
|
backendID := fmt.Sprintf("%s@%s", b.Gallery.Name, b.Name)
|
|
if backendID == galleryID || b.Name == galleryID {
|
|
isBackend = true
|
|
break
|
|
}
|
|
}
|
|
}
|
|
|
|
// Node-scoped backend ops (from /api/nodes/:id/backends/install)
|
|
// carry the nodeID inside the opcache key as "node:<nodeID>:<backend>".
|
|
// Pull it back out so the operations panel can label which node the
|
|
// install is targeting, and so the display name is just the backend
|
|
// slug instead of the full prefixed key.
|
|
scopedNodeID := ""
|
|
if nodeID, backend, ok := galleryop.ParseNodeScopedKey(galleryID); ok {
|
|
scopedNodeID = nodeID
|
|
galleryID = backend
|
|
}
|
|
|
|
// Extract display name (remove repo prefix if exists)
|
|
displayName := galleryID
|
|
if strings.Contains(galleryID, "@") {
|
|
parts := strings.Split(galleryID, "@")
|
|
if len(parts) > 1 {
|
|
displayName = parts[1]
|
|
}
|
|
}
|
|
|
|
opData := map[string]any{
|
|
"id": galleryID,
|
|
"name": displayName,
|
|
"fullName": galleryID,
|
|
"jobID": jobID,
|
|
"progress": progress,
|
|
"taskType": taskType,
|
|
"isDeletion": isDeletion,
|
|
"isBackend": isBackend,
|
|
"isQueued": isQueued,
|
|
"isCancelled": isCancelled,
|
|
"cancellable": isCancellable,
|
|
"message": message,
|
|
}
|
|
// Only attach nodeID when this op was node-scoped: an empty string
|
|
// would mislead the UI into rendering a node attribution that never
|
|
// existed in the first place.
|
|
if scopedNodeID != "" {
|
|
opData["nodeID"] = scopedNodeID
|
|
}
|
|
if status != nil && status.Error != nil {
|
|
opData["error"] = status.Error.Error()
|
|
}
|
|
// Expose the per-node breakdown when the Phase 4 progress sink
|
|
// has populated OpStatus.Nodes (distributed backend installs).
|
|
// We sort by node_name for stable UI rendering across polls;
|
|
// the underlying slice is order-dependent on UpdateNodeProgress
|
|
// arrival order, which the UI must not depend on. Single-node
|
|
// ops and model installs leave Nodes empty so this block emits
|
|
// no key, preserving the legacy payload shape.
|
|
if status != nil && len(status.Nodes) > 0 {
|
|
nodes := make([]map[string]any, 0, len(status.Nodes))
|
|
for _, n := range status.Nodes {
|
|
entry := map[string]any{
|
|
"node_id": n.NodeID,
|
|
"node_name": n.NodeName,
|
|
"status": n.Status,
|
|
"percentage": n.Percentage,
|
|
}
|
|
if n.FileName != "" {
|
|
entry["file_name"] = n.FileName
|
|
}
|
|
if n.Current != "" {
|
|
entry["current"] = n.Current
|
|
}
|
|
if n.Total != "" {
|
|
entry["total"] = n.Total
|
|
}
|
|
if n.Phase != "" {
|
|
entry["phase"] = n.Phase
|
|
}
|
|
if n.Error != "" {
|
|
entry["error"] = n.Error
|
|
}
|
|
nodes = append(nodes, entry)
|
|
}
|
|
sort.SliceStable(nodes, func(i, j int) bool {
|
|
return fmt.Sprintf("%v", nodes[i]["node_name"]) < fmt.Sprintf("%v", nodes[j]["node_name"])
|
|
})
|
|
opData["nodes"] = nodes
|
|
}
|
|
operations = append(operations, opData)
|
|
}
|
|
|
|
// Append active file staging operations (distributed mode only)
|
|
if d := applicationInstance.Distributed(); d != nil && d.Router != nil {
|
|
for modelID, status := range d.Router.StagingTracker().GetAll() {
|
|
operations = append(operations, map[string]any{
|
|
"id": "staging:" + modelID,
|
|
"name": modelID,
|
|
"fullName": modelID,
|
|
"jobID": "staging:" + modelID,
|
|
"progress": int(status.Progress),
|
|
"taskType": "staging",
|
|
"isDeletion": false,
|
|
"isBackend": false,
|
|
"isQueued": false,
|
|
"isCancelled": false,
|
|
"cancellable": false,
|
|
"message": status.Message,
|
|
"nodeName": status.NodeName,
|
|
})
|
|
}
|
|
}
|
|
|
|
// Sort operations by progress (ascending), then by ID for stable display order
|
|
slices.SortFunc(operations, func(a, b map[string]any) int {
|
|
progressA := a["progress"].(int)
|
|
progressB := b["progress"].(int)
|
|
|
|
// Primary sort by progress
|
|
if progressA != progressB {
|
|
return cmp.Compare(progressA, progressB)
|
|
}
|
|
|
|
// Secondary sort by ID for stability when progress is the same
|
|
return cmp.Compare(a["id"].(string), b["id"].(string))
|
|
})
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"operations": operations,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Cancel operation endpoint (admin only)
|
|
app.POST("/api/operations/:jobID/cancel", func(c echo.Context) error {
|
|
jobID := c.Param("jobID")
|
|
xlog.Debug("API request to cancel operation", "jobID", jobID)
|
|
|
|
err := galleryService.CancelOperation(jobID)
|
|
if err != nil {
|
|
xlog.Error("Failed to cancel operation", "error", err, "jobID", jobID)
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
// Clean up opcache for cancelled operation
|
|
opcache.DeleteUUID(jobID)
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"success": true,
|
|
"message": "Operation cancelled",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Dismiss a failed operation (acknowledge the error and remove it from the list)
|
|
app.POST("/api/operations/:jobID/dismiss", func(c echo.Context) error {
|
|
jobID := c.Param("jobID")
|
|
xlog.Debug("API request to dismiss operation", "jobID", jobID)
|
|
|
|
// Remove the operation from the opcache so it no longer appears
|
|
opcache.DeleteUUID(jobID)
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"success": true,
|
|
"message": "Operation dismissed",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Model Gallery APIs (admin only)
|
|
app.GET("/api/models", func(c echo.Context) error {
|
|
term := c.QueryParam("term")
|
|
tag := c.QueryParam("tag")
|
|
page := c.QueryParam("page")
|
|
if page == "" {
|
|
page = "1"
|
|
}
|
|
items := c.QueryParam("items")
|
|
if items == "" {
|
|
items = "9"
|
|
}
|
|
|
|
models, err := gallery.AvailableGalleryModelsCached(appConfig.Galleries, appConfig.SystemState)
|
|
if err != nil {
|
|
xlog.Error("could not list models from galleries", "error", err)
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
// Get all available tags
|
|
allTags := map[string]struct{}{}
|
|
tags := []string{}
|
|
for _, m := range models {
|
|
for _, t := range m.Tags {
|
|
allTags[t] = struct{}{}
|
|
}
|
|
}
|
|
for t := range allTags {
|
|
tags = append(tags, t)
|
|
}
|
|
slices.Sort(tags)
|
|
|
|
// Get all available backends (before filtering so dropdown always shows all)
|
|
allBackendsMap := map[string]struct{}{}
|
|
for _, m := range models {
|
|
if b := m.Backend; b != "" {
|
|
allBackendsMap[b] = struct{}{}
|
|
}
|
|
}
|
|
backendNames := make([]string, 0, len(allBackendsMap))
|
|
for b := range allBackendsMap {
|
|
backendNames = append(backendNames, b)
|
|
}
|
|
slices.Sort(backendNames)
|
|
|
|
// Filter by usecase tags (comma-separated for multi-select).
|
|
if tag != "" {
|
|
var combinedFlag config.ModelConfigUsecase
|
|
hasMultimodal := false
|
|
var plainTags []string
|
|
for _, t := range strings.Split(tag, ",") {
|
|
t = strings.TrimSpace(t)
|
|
if t == multimodalFilterKey {
|
|
hasMultimodal = true
|
|
} else if flag, ok := usecaseFilters[t]; ok {
|
|
combinedFlag |= flag
|
|
} else if t != "" {
|
|
plainTags = append(plainTags, t)
|
|
}
|
|
}
|
|
if hasMultimodal {
|
|
models = gallery.FilterGalleryModelsByMultimodal(models)
|
|
}
|
|
if combinedFlag != config.FLAG_ANY {
|
|
models = gallery.FilterGalleryModelsByUsecase(models, combinedFlag)
|
|
}
|
|
for _, pt := range plainTags {
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).FilterByTag(pt)
|
|
}
|
|
}
|
|
if term != "" {
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).Search(term)
|
|
}
|
|
|
|
// Filter by backend if requested
|
|
backendFilter := c.QueryParam("backend")
|
|
if backendFilter != "" {
|
|
var filtered gallery.GalleryElements[*gallery.GalleryModel]
|
|
for _, m := range models {
|
|
if m.Backend == backendFilter {
|
|
filtered = append(filtered, m)
|
|
}
|
|
}
|
|
models = filtered
|
|
}
|
|
|
|
// Get model statuses
|
|
processingModelsData, taskTypes := opcache.GetStatus()
|
|
|
|
// Apply sorting if requested
|
|
sortBy := c.QueryParam("sort")
|
|
sortOrder := c.QueryParam("order")
|
|
if sortOrder == "" {
|
|
sortOrder = ascSortOrder
|
|
}
|
|
|
|
switch sortBy {
|
|
case nameSortFieldName:
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).SortByName(sortOrder)
|
|
case repositorySortFieldName:
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).SortByRepository(sortOrder)
|
|
case licenseSortFieldName:
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).SortByLicense(sortOrder)
|
|
case statusSortFieldName:
|
|
models = gallery.GalleryElements[*gallery.GalleryModel](models).SortByInstalled(sortOrder)
|
|
}
|
|
|
|
pageNum, err := strconv.Atoi(page)
|
|
if err != nil || pageNum < 1 {
|
|
pageNum = 1
|
|
}
|
|
|
|
itemsNum, err := strconv.Atoi(items)
|
|
if err != nil || itemsNum < 1 {
|
|
itemsNum = 9
|
|
}
|
|
|
|
totalPages := int(math.Ceil(float64(len(models)) / float64(itemsNum)))
|
|
totalModels := len(models)
|
|
|
|
if pageNum > 0 {
|
|
models = models.Paginate(pageNum, itemsNum)
|
|
}
|
|
|
|
// Convert models to JSON-friendly format and deduplicate by ID
|
|
modelsJSON := make([]map[string]any, 0, len(models))
|
|
seenIDs := make(map[string]bool)
|
|
|
|
for _, m := range models {
|
|
modelID := m.ID()
|
|
|
|
// Skip duplicate IDs to prevent Alpine.js x-for errors
|
|
if seenIDs[modelID] {
|
|
xlog.Debug("Skipping duplicate model ID", "modelID", modelID)
|
|
continue
|
|
}
|
|
seenIDs[modelID] = true
|
|
|
|
currentlyProcessing := opcache.Exists(modelID)
|
|
jobID := ""
|
|
isDeletionOp := false
|
|
if currentlyProcessing {
|
|
jobID = opcache.Get(modelID)
|
|
status := galleryService.GetStatus(jobID)
|
|
if status != nil && status.Deletion {
|
|
isDeletionOp = true
|
|
}
|
|
}
|
|
|
|
_, trustRemoteCodeExists := m.Overrides["trust_remote_code"]
|
|
|
|
obj := map[string]any{
|
|
"id": modelID,
|
|
"name": m.Name,
|
|
"description": m.Description,
|
|
"icon": m.Icon,
|
|
"license": m.License,
|
|
"urls": m.URLs,
|
|
"tags": m.Tags,
|
|
"gallery": m.Gallery.Name,
|
|
"installed": m.Installed,
|
|
"processing": currentlyProcessing,
|
|
"jobID": jobID,
|
|
"isDeletion": isDeletionOp,
|
|
"trustRemoteCode": trustRemoteCodeExists,
|
|
"additionalFiles": m.AdditionalFiles,
|
|
"backend": m.Backend,
|
|
}
|
|
|
|
modelsJSON = append(modelsJSON, obj)
|
|
}
|
|
|
|
prevPage := pageNum - 1
|
|
nextPage := pageNum + 1
|
|
if prevPage < 1 {
|
|
prevPage = 1
|
|
}
|
|
if nextPage > totalPages {
|
|
nextPage = totalPages
|
|
}
|
|
|
|
// Calculate installed models count (models with configs + models without configs)
|
|
modelConfigs := cl.GetAllModelsConfigs()
|
|
modelsWithoutConfig, _ := galleryop.ListModels(cl, ml, config.NoFilterFn, galleryop.LOOSE_ONLY)
|
|
installedModelsCount := len(modelConfigs) + len(modelsWithoutConfig)
|
|
|
|
ramInfo, _ := xsysinfo.GetSystemRAMInfo()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"models": modelsJSON,
|
|
"repositories": appConfig.Galleries,
|
|
"allTags": tags,
|
|
"allBackends": backendNames,
|
|
"processingModels": processingModelsData,
|
|
"taskTypes": taskTypes,
|
|
"availableModels": totalModels,
|
|
"installedModels": installedModelsCount,
|
|
"ramTotal": ramInfo.Total,
|
|
"ramUsed": ramInfo.Used,
|
|
"ramUsagePercent": ramInfo.UsagePercent,
|
|
"currentPage": pageNum,
|
|
"totalPages": totalPages,
|
|
"prevPage": prevPage,
|
|
"nextPage": nextPage,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Returns installed models with their capability flags for UI filtering
|
|
app.GET("/api/models/capabilities", func(c echo.Context) error {
|
|
modelConfigs := cl.GetAllModelsConfigs()
|
|
modelsWithoutConfig, _ := galleryop.ListModels(cl, ml, config.NoFilterFn, galleryop.LOOSE_ONLY)
|
|
|
|
type loadedOn struct {
|
|
NodeID string `json:"node_id"`
|
|
NodeName string `json:"node_name"`
|
|
State string `json:"state"`
|
|
NodeStatus string `json:"node_status"`
|
|
}
|
|
type modelCapability struct {
|
|
ID string `json:"id"`
|
|
Capabilities []string `json:"capabilities"`
|
|
Backend string `json:"backend"`
|
|
Disabled bool `json:"disabled"`
|
|
Pinned bool `json:"pinned"`
|
|
// LoadedOn is populated only when the node registry is active
|
|
// (distributed mode). Lets the UI show "loaded on worker-1" without
|
|
// the operator having to expand every node manually. An empty slice
|
|
// with nil reports "no loaded replicas" vs. nil reports "not in
|
|
// cluster mode" — the frontend treats both as "no distribution info".
|
|
LoadedOn []loadedOn `json:"loaded_on,omitempty"`
|
|
// Source="registry-only" marks models adopted from the cluster that
|
|
// have no local config yet (ghosts that the reconciler discovered).
|
|
Source string `json:"source,omitempty"`
|
|
}
|
|
|
|
// Join with the node registry when we have one (distributed mode). A
|
|
// single registry fetch + map join beats per-model queries for the
|
|
// 100-model case.
|
|
var loadedByModel map[string][]loadedOn
|
|
if ds := applicationInstance.Distributed(); ds != nil && ds.Registry != nil {
|
|
nodeModels, err := ds.Registry.ListAllLoadedModels(c.Request().Context())
|
|
if err == nil {
|
|
allNodes, _ := ds.Registry.List(c.Request().Context())
|
|
nameByID := make(map[string]string, len(allNodes))
|
|
statusByID := make(map[string]string, len(allNodes))
|
|
for _, n := range allNodes {
|
|
nameByID[n.ID] = n.Name
|
|
statusByID[n.ID] = n.Status
|
|
}
|
|
loadedByModel = make(map[string][]loadedOn)
|
|
for _, nm := range nodeModels {
|
|
loadedByModel[nm.ModelName] = append(loadedByModel[nm.ModelName], loadedOn{
|
|
NodeID: nm.NodeID,
|
|
NodeName: nameByID[nm.NodeID],
|
|
State: nm.State,
|
|
NodeStatus: statusByID[nm.NodeID],
|
|
})
|
|
}
|
|
}
|
|
}
|
|
|
|
result := make([]modelCapability, 0, len(modelConfigs)+len(modelsWithoutConfig))
|
|
seen := make(map[string]bool, len(modelConfigs)+len(modelsWithoutConfig))
|
|
for _, cfg := range modelConfigs {
|
|
seen[cfg.Name] = true
|
|
result = append(result, modelCapability{
|
|
ID: cfg.Name,
|
|
Capabilities: cfg.KnownUsecaseStrings,
|
|
Backend: cfg.Backend,
|
|
Disabled: cfg.IsDisabled(),
|
|
Pinned: cfg.IsPinned(),
|
|
LoadedOn: loadedByModel[cfg.Name],
|
|
})
|
|
}
|
|
for _, name := range modelsWithoutConfig {
|
|
seen[name] = true
|
|
result = append(result, modelCapability{
|
|
ID: name,
|
|
Capabilities: []string{},
|
|
LoadedOn: loadedByModel[name],
|
|
})
|
|
}
|
|
// Emit entries for cluster models that have no local config — these
|
|
// are the actual ghosts. Without this the operator would have no way
|
|
// to see a model the cluster is running if its config file wasn't
|
|
// synced to this frontend's filesystem.
|
|
for name, loc := range loadedByModel {
|
|
if seen[name] {
|
|
continue
|
|
}
|
|
result = append(result, modelCapability{
|
|
ID: name,
|
|
Capabilities: []string{},
|
|
LoadedOn: loc,
|
|
Source: "registry-only",
|
|
})
|
|
}
|
|
|
|
// Filter by user's model allowlist if auth is enabled
|
|
if authDB := applicationInstance.AuthDB(); authDB != nil {
|
|
if user := auth.GetUser(c); user != nil && user.Role != auth.RoleAdmin {
|
|
perm, err := auth.GetCachedUserPermissions(c, authDB, user.ID)
|
|
if err == nil && perm.AllowedModels.Enabled {
|
|
allowed := map[string]bool{}
|
|
for _, m := range perm.AllowedModels.Models {
|
|
allowed[m] = true
|
|
}
|
|
filtered := make([]modelCapability, 0, len(result))
|
|
for _, mc := range result {
|
|
if allowed[mc.ID] {
|
|
filtered = append(filtered, mc)
|
|
}
|
|
}
|
|
result = filtered
|
|
}
|
|
}
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"data": result,
|
|
})
|
|
})
|
|
|
|
// Returns a mapping of backend names to the usecase filter keys they support.
|
|
// Used by the gallery frontend to grey out usecase filter buttons when a
|
|
// backend is selected.
|
|
app.GET("/api/backends/usecases", func(c echo.Context) error {
|
|
result := make(map[string][]string, len(config.BackendCapabilities))
|
|
for name, cap := range config.BackendCapabilities {
|
|
var keys []string
|
|
for _, uc := range cap.PossibleUsecases {
|
|
if _, ok := usecaseFilters[uc]; ok {
|
|
keys = append(keys, uc)
|
|
}
|
|
}
|
|
slices.Sort(keys)
|
|
result[name] = keys
|
|
}
|
|
|
|
return c.JSON(200, result)
|
|
}, adminMiddleware)
|
|
|
|
// Returns VRAM/size estimates for a single gallery model at multiple
|
|
// context sizes. The frontend calls this per-model so the gallery page
|
|
// can load instantly and fill in estimates asynchronously.
|
|
// Query params:
|
|
// contexts - comma-separated context sizes (default: 8192)
|
|
app.GET("/api/models/estimate/:id", func(c echo.Context) error {
|
|
modelID, err := url.QueryUnescape(c.Param("id"))
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{"error": "invalid model ID"})
|
|
}
|
|
|
|
contextSizes := parseContextSizes(c.QueryParam("contexts"))
|
|
|
|
// Look up the model from the gallery to build the estimate input.
|
|
models, err := gallery.AvailableGalleryModelsCached(appConfig.Galleries, appConfig.SystemState)
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{"error": err.Error()})
|
|
}
|
|
|
|
model := gallery.FindGalleryElement(models, modelID)
|
|
if model == nil {
|
|
return c.JSON(http.StatusNotFound, map[string]any{"error": "model not found"})
|
|
}
|
|
|
|
input := buildEstimateInput(model)
|
|
if len(input.Files) == 0 && input.HFRepo == "" && input.Size == "" {
|
|
return c.JSON(200, vram.MultiContextEstimate{})
|
|
}
|
|
|
|
ctx, cancel := context.WithTimeout(c.Request().Context(), 10*time.Second)
|
|
defer cancel()
|
|
result, err := vram.EstimateModelMultiContext(ctx, input, contextSizes)
|
|
if err != nil {
|
|
xlog.Debug("model estimate failed", "model", modelID, "error", err)
|
|
return c.JSON(200, vram.MultiContextEstimate{})
|
|
}
|
|
|
|
return c.JSON(200, result)
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/models/install/:id", func(c echo.Context) error {
|
|
galleryID := c.Param("id")
|
|
// URL decode the gallery ID (e.g., "localai%40model" -> "localai@model")
|
|
galleryID, err := url.QueryUnescape(galleryID)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid model ID",
|
|
})
|
|
}
|
|
xlog.Debug("API job submitted to install", "galleryID", galleryID)
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
uid := id.String()
|
|
opcache.Set(galleryID, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryModel, gallery.ModelConfig]{
|
|
ID: uid,
|
|
GalleryElementName: galleryID,
|
|
Galleries: appConfig.Galleries,
|
|
BackendGalleries: appConfig.BackendGalleries,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
go func() {
|
|
galleryService.ModelGalleryChannel <- op
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"message": "Installation started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/models/delete/:id", func(c echo.Context) error {
|
|
galleryID := c.Param("id")
|
|
// URL decode the gallery ID
|
|
galleryID, err := url.QueryUnescape(galleryID)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid model ID",
|
|
})
|
|
}
|
|
xlog.Debug("API job submitted to delete", "galleryID", galleryID)
|
|
|
|
var galleryName = galleryID
|
|
if strings.Contains(galleryID, "@") {
|
|
galleryName = strings.Split(galleryID, "@")[1]
|
|
}
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
uid := id.String()
|
|
|
|
opcache.Set(galleryID, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryModel, gallery.ModelConfig]{
|
|
ID: uid,
|
|
Delete: true,
|
|
GalleryElementName: galleryName,
|
|
Galleries: appConfig.Galleries,
|
|
BackendGalleries: appConfig.BackendGalleries,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
go func() {
|
|
galleryService.ModelGalleryChannel <- op
|
|
cl.RemoveModelConfig(galleryName)
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"message": "Deletion started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/models/config/:id", func(c echo.Context) error {
|
|
galleryID := c.Param("id")
|
|
// URL decode the gallery ID
|
|
galleryID, err := url.QueryUnescape(galleryID)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid model ID",
|
|
})
|
|
}
|
|
xlog.Debug("API job submitted to get config", "galleryID", galleryID)
|
|
|
|
models, err := gallery.AvailableGalleryModelsCached(appConfig.Galleries, appConfig.SystemState)
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
model := gallery.FindGalleryElement(models, galleryID)
|
|
if model == nil {
|
|
return c.JSON(http.StatusNotFound, map[string]any{
|
|
"error": "model not found",
|
|
})
|
|
}
|
|
|
|
config, err := gallery.GetGalleryConfigFromURL[gallery.ModelConfig](model.URL, appConfig.SystemState.Model.ModelsPath)
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
_, err = gallery.InstallModel(context.Background(), appConfig.SystemState, model.Name, &config, model.Overrides, nil, false)
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"message": "Configuration file saved",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Get installed model config as JSON (used by frontend for MCP detection, etc.)
|
|
app.GET("/api/models/config-json/:name", func(c echo.Context) error {
|
|
modelName := c.Param("name")
|
|
if modelName == "" {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "model name is required",
|
|
})
|
|
}
|
|
|
|
modelConfig, exists := cl.GetModelConfig(modelName)
|
|
if !exists {
|
|
return c.JSON(http.StatusNotFound, map[string]any{
|
|
"error": "model configuration not found",
|
|
})
|
|
}
|
|
|
|
return c.JSON(http.StatusOK, modelConfig)
|
|
}, adminMiddleware)
|
|
|
|
// Config metadata API - returns field metadata for all ~170 config fields
|
|
app.GET("/api/models/config-metadata", localai.ConfigMetadataEndpoint(), adminMiddleware)
|
|
|
|
// Autocomplete providers for config fields (dynamic values only)
|
|
app.GET("/api/models/config-metadata/autocomplete/:provider", localai.AutocompleteEndpoint(cl, ml, appConfig), adminMiddleware)
|
|
|
|
// PATCH config endpoint - partial update using nested JSON merge
|
|
app.PATCH("/api/models/config-json/:name", localai.PatchConfigEndpoint(cl, ml, appConfig), adminMiddleware)
|
|
|
|
// VRAM estimation endpoint
|
|
app.POST("/api/models/vram-estimate", localai.VRAMEstimateEndpoint(cl, appConfig), adminMiddleware)
|
|
|
|
// Get installed model YAML config for the React model editor
|
|
app.GET("/api/models/edit/:name", func(c echo.Context) error {
|
|
modelName := c.Param("name")
|
|
if decoded, err := url.PathUnescape(modelName); err == nil {
|
|
modelName = decoded
|
|
}
|
|
if modelName == "" {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "model name is required",
|
|
})
|
|
}
|
|
|
|
modelConfig, exists := cl.GetModelConfig(modelName)
|
|
if !exists {
|
|
return c.JSON(http.StatusNotFound, map[string]any{
|
|
"error": "model configuration not found",
|
|
})
|
|
}
|
|
|
|
modelConfigFile := modelConfig.GetModelConfigFile()
|
|
if modelConfigFile == "" {
|
|
return c.JSON(http.StatusNotFound, map[string]any{
|
|
"error": "model configuration file not found",
|
|
})
|
|
}
|
|
|
|
configData, err := os.ReadFile(modelConfigFile)
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": "failed to read configuration file: " + err.Error(),
|
|
})
|
|
}
|
|
|
|
return c.JSON(http.StatusOK, map[string]any{
|
|
"config": string(configData),
|
|
"name": modelName,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.GET("/api/models/job/:uid", func(c echo.Context) error {
|
|
jobUID := c.Param("uid")
|
|
|
|
status := galleryService.GetStatus(jobUID)
|
|
if status == nil {
|
|
// Job is queued but hasn't started processing yet
|
|
return c.JSON(200, map[string]any{
|
|
"progress": 0,
|
|
"message": "Operation queued",
|
|
"galleryElementName": "",
|
|
"processed": false,
|
|
"deletion": false,
|
|
"queued": true,
|
|
})
|
|
}
|
|
|
|
response := map[string]any{
|
|
"progress": status.Progress,
|
|
"message": status.Message,
|
|
"galleryElementName": status.GalleryElementName,
|
|
"processed": status.Processed,
|
|
"deletion": status.Deletion,
|
|
"queued": false,
|
|
}
|
|
|
|
if status.Error != nil {
|
|
response["error"] = status.Error.Error()
|
|
}
|
|
|
|
if status.Progress == 100 && status.Processed && status.Message == "completed" {
|
|
opcache.DeleteUUID(jobUID)
|
|
response["completed"] = true
|
|
}
|
|
|
|
return c.JSON(200, response)
|
|
}, adminMiddleware)
|
|
|
|
// Backend Gallery APIs
|
|
app.GET("/api/backends", func(c echo.Context) error {
|
|
term := c.QueryParam("term")
|
|
tag := c.QueryParam("tag")
|
|
page := c.QueryParam("page")
|
|
if page == "" {
|
|
page = "1"
|
|
}
|
|
items := c.QueryParam("items")
|
|
if items == "" {
|
|
items = "9"
|
|
}
|
|
|
|
backends, err := gallery.AvailableBackendsUnfiltered(appConfig.BackendGalleries, appConfig.SystemState)
|
|
if err != nil {
|
|
xlog.Error("could not list backends from galleries", "error", err)
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
// Collect concrete backend names that are referenced by any meta backend's
|
|
// CapabilitiesMap. These are the per-capability variants the UI hides by
|
|
// default behind "Show all" (the meta backend is the preferred entry).
|
|
aliasedByMeta := make(map[string]bool)
|
|
for _, b := range backends {
|
|
if !b.IsMeta() {
|
|
continue
|
|
}
|
|
for _, concreteName := range b.CapabilitiesMap {
|
|
aliasedByMeta[concreteName] = true
|
|
}
|
|
}
|
|
|
|
// Use the BackendManager's list to determine installed status.
|
|
// In standalone mode this checks the local filesystem; in distributed
|
|
// mode it aggregates from all healthy worker nodes.
|
|
installedBackends, listErr := galleryService.ListBackends()
|
|
if listErr == nil {
|
|
for i, b := range backends {
|
|
if installedBackends.Exists(b.GetName()) {
|
|
backends[i].Installed = true
|
|
}
|
|
}
|
|
}
|
|
|
|
// Get all available tags
|
|
allTags := map[string]struct{}{}
|
|
tags := []string{}
|
|
for _, b := range backends {
|
|
for _, t := range b.Tags {
|
|
allTags[t] = struct{}{}
|
|
}
|
|
}
|
|
for t := range allTags {
|
|
tags = append(tags, t)
|
|
}
|
|
slices.Sort(tags)
|
|
|
|
if tag != "" {
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).FilterByTag(tag)
|
|
}
|
|
if term != "" {
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).Search(term)
|
|
}
|
|
|
|
// Get backend statuses
|
|
processingBackendsData, taskTypes := opcache.GetStatus()
|
|
|
|
// Apply sorting if requested
|
|
sortBy := c.QueryParam("sort")
|
|
sortOrder := c.QueryParam("order")
|
|
if sortOrder == "" {
|
|
sortOrder = ascSortOrder
|
|
}
|
|
|
|
switch sortBy {
|
|
case nameSortFieldName:
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).SortByName(sortOrder)
|
|
case repositorySortFieldName:
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).SortByRepository(sortOrder)
|
|
case licenseSortFieldName:
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).SortByLicense(sortOrder)
|
|
case statusSortFieldName:
|
|
backends = gallery.GalleryElements[*gallery.GalleryBackend](backends).SortByInstalled(sortOrder)
|
|
}
|
|
|
|
pageNum, err := strconv.Atoi(page)
|
|
if err != nil || pageNum < 1 {
|
|
pageNum = 1
|
|
}
|
|
|
|
itemsNum, err := strconv.Atoi(items)
|
|
if err != nil || itemsNum < 1 {
|
|
itemsNum = 9
|
|
}
|
|
|
|
totalPages := int(math.Ceil(float64(len(backends)) / float64(itemsNum)))
|
|
totalBackends := len(backends)
|
|
|
|
if pageNum > 0 {
|
|
backends = backends.Paginate(pageNum, itemsNum)
|
|
}
|
|
|
|
// Get dev suffix from SystemState for development backend detection
|
|
devSuffix := ""
|
|
if appConfig.SystemState != nil {
|
|
devSuffix = appConfig.SystemState.BackendDevSuffix
|
|
}
|
|
|
|
// Convert backends to JSON-friendly format and deduplicate by ID
|
|
backendsJSON := make([]map[string]any, 0, len(backends))
|
|
seenBackendIDs := make(map[string]bool)
|
|
|
|
for _, b := range backends {
|
|
backendID := b.ID()
|
|
|
|
// Skip duplicate IDs to prevent Alpine.js x-for errors
|
|
if seenBackendIDs[backendID] {
|
|
xlog.Debug("Skipping duplicate backend ID", "backendID", backendID)
|
|
continue
|
|
}
|
|
seenBackendIDs[backendID] = true
|
|
|
|
currentlyProcessing := opcache.Exists(backendID)
|
|
jobID := ""
|
|
isDeletionOp := false
|
|
if currentlyProcessing {
|
|
jobID = opcache.Get(backendID)
|
|
status := galleryService.GetStatus(jobID)
|
|
if status != nil && status.Deletion {
|
|
isDeletionOp = true
|
|
}
|
|
}
|
|
|
|
// Per-node distribution + parent meta lookup for the install picker.
|
|
// `nodes` populates the Nodes column on the gallery; `metaBackendFor`
|
|
// lets the picker name the parent (e.g. "CPU build of llama-cpp")
|
|
// without re-walking the whole gallery on the client.
|
|
var perNode []gallery.NodeBackendRef
|
|
if installedBackends != nil {
|
|
if sb, ok := installedBackends.Get(b.Name); ok {
|
|
perNode = sb.Nodes
|
|
}
|
|
}
|
|
|
|
backendsJSON = append(backendsJSON, map[string]any{
|
|
"id": backendID,
|
|
"name": b.Name,
|
|
"description": b.Description,
|
|
"icon": b.Icon,
|
|
"license": b.License,
|
|
"urls": b.URLs,
|
|
"tags": b.Tags,
|
|
"gallery": b.Gallery.Name,
|
|
"installed": b.Installed,
|
|
"version": b.Version,
|
|
"processing": currentlyProcessing,
|
|
"jobID": jobID,
|
|
"isDeletion": isDeletionOp,
|
|
"isMeta": b.IsMeta(),
|
|
"isAlias": aliasedByMeta[b.Name],
|
|
"isDevelopment": b.IsDevelopment(devSuffix),
|
|
"capabilities": b.CapabilitiesMap,
|
|
"metaBackendFor": metaParentOf(b.Name, backends),
|
|
"nodes": perNode,
|
|
})
|
|
}
|
|
|
|
prevPage := pageNum - 1
|
|
nextPage := pageNum + 1
|
|
if prevPage < 1 {
|
|
prevPage = 1
|
|
}
|
|
if nextPage > totalPages {
|
|
nextPage = totalPages
|
|
}
|
|
|
|
// Calculate installed backends count (reuse the already-fetched data)
|
|
installedBackendsCount := 0
|
|
if listErr == nil {
|
|
installedBackendsCount = len(installedBackends)
|
|
} else {
|
|
// Fallback to local listing if manager listing failed
|
|
if localBackends, localErr := gallery.ListSystemBackends(appConfig.SystemState); localErr == nil {
|
|
installedBackendsCount = len(localBackends)
|
|
}
|
|
}
|
|
|
|
// Get the detected system capability
|
|
detectedCapability := ""
|
|
if appConfig.SystemState != nil {
|
|
detectedCapability = appConfig.SystemState.DetectedCapability()
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"backends": backendsJSON,
|
|
"repositories": appConfig.BackendGalleries,
|
|
"allTags": tags,
|
|
"processingBackends": processingBackendsData,
|
|
"taskTypes": taskTypes,
|
|
"availableBackends": totalBackends,
|
|
"installedBackends": installedBackendsCount,
|
|
"currentPage": pageNum,
|
|
"totalPages": totalPages,
|
|
"prevPage": prevPage,
|
|
"nextPage": nextPage,
|
|
"systemCapability": detectedCapability,
|
|
"preferDevelopmentBackends": appConfig.PreferDevelopmentBackends,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/backends/install/:id", func(c echo.Context) error {
|
|
backendID := c.Param("id")
|
|
// URL decode the backend ID
|
|
backendID, err := url.QueryUnescape(backendID)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid backend ID",
|
|
})
|
|
}
|
|
xlog.Debug("API job submitted to install backend", "backendID", backendID)
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
uid := id.String()
|
|
opcache.SetBackend(backendID, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryBackend, any]{
|
|
ID: uid,
|
|
GalleryElementName: backendID,
|
|
Galleries: appConfig.BackendGalleries,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
go func() {
|
|
galleryService.BackendGalleryChannel <- op
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"message": "Backend installation started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Install backend from external source (OCI image, URL, or path)
|
|
app.POST("/api/backends/install-external", func(c echo.Context) error {
|
|
// Request body structure
|
|
type ExternalBackendRequest struct {
|
|
URI string `json:"uri"`
|
|
Name string `json:"name"`
|
|
Alias string `json:"alias"`
|
|
}
|
|
|
|
var req ExternalBackendRequest
|
|
if err := c.Bind(&req); err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid request body",
|
|
})
|
|
}
|
|
|
|
// Validate required fields
|
|
if req.URI == "" {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "uri is required",
|
|
})
|
|
}
|
|
|
|
xlog.Debug("API job submitted to install external backend", "uri", req.URI, "name", req.Name, "alias", req.Alias)
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
uid := id.String()
|
|
|
|
// Use URI as the key for opcache, or name if provided
|
|
cacheKey := req.URI
|
|
if req.Name != "" {
|
|
cacheKey = req.Name
|
|
}
|
|
opcache.SetBackend(cacheKey, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryBackend, any]{
|
|
ID: uid,
|
|
GalleryElementName: req.Name, // May be empty, will be derived during installation
|
|
Galleries: appConfig.BackendGalleries,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
ExternalURI: req.URI,
|
|
ExternalName: req.Name,
|
|
ExternalAlias: req.Alias,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
go func() {
|
|
galleryService.BackendGalleryChannel <- op
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"message": "External backend installation started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/backends/delete/:id", func(c echo.Context) error {
|
|
backendID := c.Param("id")
|
|
// URL decode the backend ID
|
|
backendID, err := url.QueryUnescape(backendID)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid backend ID",
|
|
})
|
|
}
|
|
xlog.Debug("API job submitted to delete backend", "backendID", backendID)
|
|
|
|
var backendName = backendID
|
|
if strings.Contains(backendID, "@") {
|
|
backendName = strings.Split(backendID, "@")[1]
|
|
}
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
uid := id.String()
|
|
|
|
opcache.SetBackend(backendID, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryBackend, any]{
|
|
ID: uid,
|
|
Delete: true,
|
|
GalleryElementName: backendName,
|
|
Galleries: appConfig.BackendGalleries,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
go func() {
|
|
galleryService.BackendGalleryChannel <- op
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"message": "Backend deletion started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.GET("/api/backends/job/:uid", func(c echo.Context) error {
|
|
jobUID := c.Param("uid")
|
|
|
|
status := galleryService.GetStatus(jobUID)
|
|
if status == nil {
|
|
// Job is queued but hasn't started processing yet
|
|
return c.JSON(200, map[string]any{
|
|
"progress": 0,
|
|
"message": "Operation queued",
|
|
"galleryElementName": "",
|
|
"processed": false,
|
|
"deletion": false,
|
|
"queued": true,
|
|
})
|
|
}
|
|
|
|
response := map[string]any{
|
|
"progress": status.Progress,
|
|
"message": status.Message,
|
|
"galleryElementName": status.GalleryElementName,
|
|
"processed": status.Processed,
|
|
"deletion": status.Deletion,
|
|
"queued": false,
|
|
}
|
|
|
|
if status.Error != nil {
|
|
response["error"] = status.Error.Error()
|
|
}
|
|
|
|
if status.Progress == 100 && status.Processed && status.Message == "completed" {
|
|
opcache.DeleteUUID(jobUID)
|
|
response["completed"] = true
|
|
}
|
|
|
|
return c.JSON(200, response)
|
|
}, adminMiddleware)
|
|
|
|
// System Backend Deletion API (for installed backends on index page)
|
|
app.POST("/api/backends/system/delete/:name", func(c echo.Context) error {
|
|
backendName := c.Param("name")
|
|
// URL decode the backend name
|
|
backendName, err := url.QueryUnescape(backendName)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid backend name",
|
|
})
|
|
}
|
|
xlog.Debug("API request to delete system backend", "backendName", backendName)
|
|
|
|
// Use the gallery service's backend manager, which in distributed mode
|
|
// fans out deletion to worker nodes via NATS.
|
|
if err := galleryService.DeleteBackend(backendName); err != nil {
|
|
xlog.Error("Failed to delete backend", "error", err, "backendName", backendName)
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
})
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"success": true,
|
|
"message": "Backend deleted successfully",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Backend upgrade APIs
|
|
app.GET("/api/backends/upgrades", func(c echo.Context) error {
|
|
if applicationInstance == nil || applicationInstance.UpgradeChecker() == nil {
|
|
return c.JSON(200, map[string]any{})
|
|
}
|
|
return c.JSON(200, applicationInstance.UpgradeChecker().GetAvailableUpgrades())
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/backends/upgrades/check", func(c echo.Context) error {
|
|
if applicationInstance == nil || applicationInstance.UpgradeChecker() == nil {
|
|
return c.JSON(200, map[string]any{})
|
|
}
|
|
applicationInstance.UpgradeChecker().TriggerCheck()
|
|
return c.JSON(200, applicationInstance.UpgradeChecker().GetAvailableUpgrades())
|
|
}, adminMiddleware)
|
|
|
|
app.POST("/api/backends/upgrade/:name", func(c echo.Context) error {
|
|
backendName := c.Param("name")
|
|
backendName, err := url.QueryUnescape(backendName)
|
|
if err != nil {
|
|
return c.JSON(http.StatusBadRequest, map[string]any{
|
|
"error": "invalid backend name",
|
|
})
|
|
}
|
|
|
|
id, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return c.JSON(http.StatusInternalServerError, map[string]any{"error": err.Error()})
|
|
}
|
|
|
|
uid := id.String()
|
|
|
|
// Register in opcache so the operation shows up in /api/operations
|
|
// and the Backends UI can reflect progress on the affected row.
|
|
opcache.SetBackend(backendName, uid)
|
|
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
op := galleryop.ManagementOp[gallery.GalleryBackend, any]{
|
|
ID: uid,
|
|
GalleryElementName: backendName,
|
|
Galleries: appConfig.BackendGalleries,
|
|
Upgrade: true,
|
|
Context: ctx,
|
|
CancelFunc: cancelFunc,
|
|
}
|
|
// Store cancellation function immediately so queued operations can be cancelled
|
|
galleryService.StoreCancellation(uid, cancelFunc)
|
|
// Non-blocking send — BackendGalleryChannel is unbuffered and a direct
|
|
// send would hang the HTTP handler whenever the worker is busy.
|
|
go func() {
|
|
galleryService.BackendGalleryChannel <- op
|
|
}()
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"jobID": uid,
|
|
"uuid": uid,
|
|
"statusUrl": fmt.Sprintf("/api/backends/job/%s", uid),
|
|
"message": "Backend upgrade started",
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// P2P APIs
|
|
app.GET("/api/p2p/workers", func(c echo.Context) error {
|
|
llamaNodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.LlamaCPPWorkerID))
|
|
mlxNodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.MLXWorkerID))
|
|
|
|
llamaJSON := make([]map[string]any, 0, len(llamaNodes))
|
|
for _, n := range llamaNodes {
|
|
llamaJSON = append(llamaJSON, map[string]any{
|
|
"name": n.Name,
|
|
"id": n.ID,
|
|
"tunnelAddress": n.TunnelAddress,
|
|
"serviceID": n.ServiceID,
|
|
"lastSeen": n.LastSeen,
|
|
"isOnline": n.IsOnline(),
|
|
})
|
|
}
|
|
|
|
mlxJSON := make([]map[string]any, 0, len(mlxNodes))
|
|
for _, n := range mlxNodes {
|
|
mlxJSON = append(mlxJSON, map[string]any{
|
|
"name": n.Name,
|
|
"id": n.ID,
|
|
"tunnelAddress": n.TunnelAddress,
|
|
"serviceID": n.ServiceID,
|
|
"lastSeen": n.LastSeen,
|
|
"isOnline": n.IsOnline(),
|
|
})
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"llama_cpp": map[string]any{
|
|
"nodes": llamaJSON,
|
|
},
|
|
"mlx": map[string]any{
|
|
"nodes": mlxJSON,
|
|
},
|
|
// Keep backward-compatible "nodes" key with llama.cpp workers
|
|
"nodes": llamaJSON,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.GET("/api/p2p/federation", func(c echo.Context) error {
|
|
nodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.FederatedID))
|
|
|
|
nodesJSON := make([]map[string]any, 0, len(nodes))
|
|
for _, n := range nodes {
|
|
nodesJSON = append(nodesJSON, map[string]any{
|
|
"name": n.Name,
|
|
"id": n.ID,
|
|
"tunnelAddress": n.TunnelAddress,
|
|
"serviceID": n.ServiceID,
|
|
"lastSeen": n.LastSeen,
|
|
"isOnline": n.IsOnline(),
|
|
})
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"nodes": nodesJSON,
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
app.GET("/api/p2p/stats", func(c echo.Context) error {
|
|
llamaCPPNodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.LlamaCPPWorkerID))
|
|
federatedNodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.FederatedID))
|
|
mlxWorkerNodes := p2p.GetAvailableNodes(p2p.NetworkID(appConfig.P2PNetworkID, p2p.MLXWorkerID))
|
|
|
|
llamaCPPOnline := 0
|
|
for _, n := range llamaCPPNodes {
|
|
if n.IsOnline() {
|
|
llamaCPPOnline++
|
|
}
|
|
}
|
|
|
|
federatedOnline := 0
|
|
for _, n := range federatedNodes {
|
|
if n.IsOnline() {
|
|
federatedOnline++
|
|
}
|
|
}
|
|
|
|
mlxWorkersOnline := 0
|
|
for _, n := range mlxWorkerNodes {
|
|
if n.IsOnline() {
|
|
mlxWorkersOnline++
|
|
}
|
|
}
|
|
|
|
return c.JSON(200, map[string]any{
|
|
"llama_cpp_workers": map[string]any{
|
|
"online": llamaCPPOnline,
|
|
"total": len(llamaCPPNodes),
|
|
},
|
|
"federated": map[string]any{
|
|
"online": federatedOnline,
|
|
"total": len(federatedNodes),
|
|
},
|
|
"mlx_workers": map[string]any{
|
|
"online": mlxWorkersOnline,
|
|
"total": len(mlxWorkerNodes),
|
|
},
|
|
})
|
|
}, adminMiddleware)
|
|
|
|
// Resources API endpoint - unified memory info (GPU if available, otherwise RAM)
|
|
app.GET("/api/resources", func(c echo.Context) error {
|
|
resourceInfo := xsysinfo.GetResourceInfo()
|
|
|
|
// Format watchdog interval
|
|
watchdogInterval := "2s" // default
|
|
if appConfig.WatchDogInterval > 0 {
|
|
watchdogInterval = appConfig.WatchDogInterval.String()
|
|
}
|
|
|
|
storageSize, _ := getDirectorySize(appConfig.SystemState.Model.ModelsPath)
|
|
|
|
response := map[string]any{
|
|
"type": resourceInfo.Type, // "gpu" or "ram"
|
|
"available": resourceInfo.Available,
|
|
"gpus": resourceInfo.GPUs,
|
|
"ram": resourceInfo.RAM,
|
|
"aggregate": resourceInfo.Aggregate,
|
|
"storage_size": storageSize,
|
|
"reclaimer_enabled": appConfig.MemoryReclaimerEnabled,
|
|
"reclaimer_threshold": appConfig.MemoryReclaimerThreshold,
|
|
"watchdog_interval": watchdogInterval,
|
|
}
|
|
|
|
return c.JSON(200, response)
|
|
}, adminMiddleware)
|
|
|
|
if !appConfig.DisableRuntimeSettings {
|
|
// Settings API
|
|
app.GET("/api/settings", localai.GetSettingsEndpoint(applicationInstance), adminMiddleware)
|
|
app.POST("/api/settings", localai.UpdateSettingsEndpoint(applicationInstance), adminMiddleware)
|
|
}
|
|
|
|
// Branding / whitelabeling. The read endpoint and the asset server are
|
|
// public so the login screen can render the configured logo and instance
|
|
// name before authentication. Mutations are admin-only. See app.go where
|
|
// "/api/branding" and "/branding/" are added to PathWithoutAuth.
|
|
app.GET("/api/branding", localai.GetBrandingEndpoint(appConfig))
|
|
app.GET("/branding/asset/:kind", localai.ServeBrandingAssetEndpoint(appConfig))
|
|
app.POST("/api/branding/asset/:kind", localai.UploadBrandingAssetEndpoint(appConfig), adminMiddleware)
|
|
app.DELETE("/api/branding/asset/:kind", localai.DeleteBrandingAssetEndpoint(appConfig), adminMiddleware)
|
|
|
|
}
|