mirror of
https://github.com/mudler/LocalAI.git
synced 2026-08-03 03:53:15 -04:00
Two lifecycle defects observed on a 2-replica distributed cluster. The install endpoints mint a job UUID, hand the operation to an unbuffered channel, and answer HTTP 200 immediately. The gallery worker is a single goroutine that processes operations serially, and the first status write happens inside modelHandler/backendHandler — i.e. only once the worker actually starts the work. An operation queued behind a running install therefore had no status at all: GET /models/jobs/<uuid> answered "could not find any status for ID" and GET /models/jobs did not list it, so the endpoint reported success for work nothing could observe. On the paths that sent directly rather than from a goroutine, the same unbuffered channel blocked the HTTP handler for the whole duration of the in-flight install, which is how a replica came to accept no /models/apply at all while /readyz stayed green. Admission now goes through EnqueueModelOp/EnqueueBackendOp, which publish a "queued" status before handing the operation over, so a job ID is queryable from the instant it is handed out. Delivery selects on the operation's context, so cancelling a still-queued operation releases the delivery goroutine instead of stranding it on a send that will never be received, and an operation the worker never accepts becomes a terminal failure rather than a silent leak. The worker also had no panic containment. A panic in any handler propagated out of the single consumer goroutine and killed the process, taking every queued operation with it; it is now contained to the operation that caused it. The two ignored galleryStore.Create errors are logged, and the model and backend delete endpoints now run under the same ID they hand back — they previously ran under an empty ID and returned a status URL for a job that could never have a status. Second, an operation orphaned by a controller replaced mid-download kept reporting phase=downloading, processed=false, error=none while nothing was downloading. The PostgreSQL side does recover on its own (FindDuplicate ignores rows untouched for 30 minutes and CleanStale marks them failed), but the reaper only ever corrected the database. The in-memory statuses map that GET /models/jobs/<id> and /api/operations actually read was never corrected, so every replica kept serving the frozen tick indefinitely. ReapStaleOperations now reconciles the in-memory copy with the reap. Note that operation ownership is still not tracked: gallery_operations has a FrontendID column that nothing writes, so a live operation and one whose owner died are distinguished only by a 30-minute staleness timeout. Narrowing that window needs a lease/heartbeat mechanism and is out of scope here. 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>
181 lines
6.1 KiB
Go
181 lines
6.1 KiB
Go
package localai
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
|
|
"github.com/google/uuid"
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/gallery"
|
|
"github.com/mudler/LocalAI/core/http/middleware"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/services/galleryop"
|
|
"github.com/mudler/LocalAI/pkg/system"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
type ModelGalleryEndpointService struct {
|
|
galleries []config.Gallery
|
|
backendGalleries []config.Gallery
|
|
modelPath string
|
|
galleryApplier *galleryop.GalleryService
|
|
configLoader *config.ModelConfigLoader
|
|
}
|
|
|
|
type GalleryModel struct {
|
|
ID string `json:"id"`
|
|
// Variant installs one specific build of an entry that declares variants,
|
|
// named as it appears in the entry's `variants` list (see the `variants`
|
|
// and `auto_variant` fields of the gallery listing). Leave it empty to let
|
|
// LocalAI auto-select the largest build this host can actually run.
|
|
Variant string `json:"variant,omitempty"`
|
|
gallery.GalleryModel
|
|
}
|
|
|
|
func CreateModelGalleryEndpointService(galleries []config.Gallery, backendGalleries []config.Gallery, systemState *system.SystemState, galleryApplier *galleryop.GalleryService, configLoader *config.ModelConfigLoader) ModelGalleryEndpointService {
|
|
return ModelGalleryEndpointService{
|
|
galleries: galleries,
|
|
backendGalleries: backendGalleries,
|
|
modelPath: systemState.Model.ModelsPath,
|
|
galleryApplier: galleryApplier,
|
|
configLoader: configLoader,
|
|
}
|
|
}
|
|
|
|
// GetOpStatusEndpoint returns the job status
|
|
// @Summary Returns the job status
|
|
// @Tags models
|
|
// @Success 200 {object} galleryop.OpStatus "Response"
|
|
// @Router /models/jobs/{uuid} [get]
|
|
func (mgs *ModelGalleryEndpointService) GetOpStatusEndpoint() echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
status := mgs.galleryApplier.GetStatus(c.Param("uuid"))
|
|
if status == nil {
|
|
return fmt.Errorf("could not find any status for ID")
|
|
}
|
|
return c.JSON(200, status)
|
|
}
|
|
}
|
|
|
|
// GetAllStatusEndpoint returns all the jobs status progress
|
|
// @Summary Returns all the jobs status progress
|
|
// @Tags models
|
|
// @Success 200 {object} map[string]galleryop.OpStatus "Response"
|
|
// @Router /models/jobs [get]
|
|
func (mgs *ModelGalleryEndpointService) GetAllStatusEndpoint() echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
return c.JSON(200, mgs.galleryApplier.GetAllStatus())
|
|
}
|
|
}
|
|
|
|
// ApplyModelGalleryEndpoint installs a new model to a LocalAI instance from the model gallery
|
|
// @Summary Install models to LocalAI.
|
|
// @Tags models
|
|
// @Param request body GalleryModel true "query params"
|
|
// @Success 200 {object} schema.GalleryResponse "Response"
|
|
// @Router /models/apply [post]
|
|
func (mgs *ModelGalleryEndpointService) ApplyModelGalleryEndpoint() echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
input := new(GalleryModel)
|
|
// Get input data from the request body
|
|
if err := c.Bind(input); err != nil {
|
|
return err
|
|
}
|
|
|
|
uuid, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
mgs.galleryApplier.EnqueueModelOp(galleryop.ManagementOp[gallery.GalleryModel, gallery.ModelConfig]{
|
|
Req: input.GalleryModel,
|
|
ID: uuid.String(),
|
|
GalleryElementName: input.ID,
|
|
Variant: input.Variant,
|
|
Galleries: mgs.galleries,
|
|
BackendGalleries: mgs.backendGalleries,
|
|
})
|
|
|
|
return c.JSON(200, schema.GalleryResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%smodels/jobs/%s", middleware.BaseURL(c), uuid.String())})
|
|
}
|
|
}
|
|
|
|
// DeleteModelGalleryEndpoint lets delete models from a LocalAI instance
|
|
// @Summary delete models to LocalAI.
|
|
// @Tags models
|
|
// @Param name path string true "Model name"
|
|
// @Success 200 {object} schema.GalleryResponse "Response"
|
|
// @Router /models/delete/{name} [post]
|
|
func (mgs *ModelGalleryEndpointService) DeleteModelGalleryEndpoint() echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
modelName := c.Param("name")
|
|
|
|
uuid, err := uuid.NewUUID()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
// The op carries the same ID the caller is handed back: without it the
|
|
// deletion ran under an empty ID and StatusURL pointed at a job that
|
|
// could never have a status.
|
|
mgs.galleryApplier.EnqueueModelOp(galleryop.ManagementOp[gallery.GalleryModel, gallery.ModelConfig]{
|
|
ID: uuid.String(),
|
|
Delete: true,
|
|
GalleryElementName: modelName,
|
|
})
|
|
|
|
mgs.configLoader.RemoveModelConfig(modelName)
|
|
|
|
return c.JSON(200, schema.GalleryResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%smodels/jobs/%s", middleware.BaseURL(c), uuid.String())})
|
|
}
|
|
}
|
|
|
|
// ListModelFromGalleryEndpoint list the available models for installation from the active galleries
|
|
// @Summary List installable models.
|
|
// @Tags models
|
|
// @Success 200 {object} []gallery.Metadata "Response"
|
|
// @Router /models/available [get]
|
|
func (mgs *ModelGalleryEndpointService) ListModelFromGalleryEndpoint(systemState *system.SystemState) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
|
|
models, err := gallery.AvailableGalleryModels(mgs.galleries, systemState)
|
|
if err != nil {
|
|
xlog.Error("could not list models from galleries", "error", err)
|
|
return err
|
|
}
|
|
|
|
xlog.Debug("Available models from galleries", "modelCount", len(models), "galleryCount", len(mgs.galleries))
|
|
|
|
m := []gallery.Metadata{}
|
|
|
|
for _, mm := range models {
|
|
m = append(m, mm.Metadata)
|
|
}
|
|
|
|
xlog.Debug("Models", "models", m)
|
|
|
|
dat, err := json.Marshal(m)
|
|
if err != nil {
|
|
return fmt.Errorf("could not marshal models: %w", err)
|
|
}
|
|
return c.Blob(200, "application/json", dat)
|
|
}
|
|
}
|
|
|
|
// ListModelGalleriesEndpoint list the available galleries configured in LocalAI
|
|
// @Summary List all Galleries
|
|
// @Tags models
|
|
// @Success 200 {object} []config.Gallery "Response"
|
|
// @Router /models/galleries [get]
|
|
// NOTE: This is different (and much simpler!) than above! This JUST lists the model galleries that have been loaded, not their contents!
|
|
func (mgs *ModelGalleryEndpointService) ListModelGalleriesEndpoint() echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
xlog.Debug("Listing model galleries", "galleries", mgs.galleries)
|
|
dat, err := json.Marshal(mgs.galleries)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return c.Blob(200, "application/json", dat)
|
|
}
|
|
}
|