Files
LocalAI/core/services/distributed/quant.go
LocalAI [bot] d7d7721eae feat(distributed): SyncedMap component + migrate finetune/quant/agent-tasks to cross-replica state (#10542)
* feat(distributed): add SyncedMap cross-replica in-memory state component

Introduce core/services/syncstate.SyncedMap[K,V]: a thread-safe in-memory map
that keeps itself consistent across frontend replicas via NATS, with an optional
pluggable durable Store and hydrate-from-source convergence.

Several features keep process-local state surfaced to the API (finetune/quant
jobs, agent tasks, model configs) and each hand-wired the same in-memory + NATS
broadcast + read-through-store legs - or forgot to, reintroducing cross-replica
staleness. SyncedMap makes that consistency a configuration choice:

- local writes mutate the map, write through the Store, then broadcast a delta;
- the apply path is memory-only and never re-publishes or re-writes the Store
  (structural echo-loop guard, mirroring galleryop.mergeStatus);
- on Start and on NATS reconnect the map re-hydrates from the source (Store, else
  Loader); an optional periodic Reconcile repairs silent drift;
- standalone mode (nil NATS client) is a strict in-memory no-op.

Reconnect re-hydrate is wired via a new *messaging.Client.OnReconnect callback,
consumed through an optional type-assertion so MessagingClient stays minimal.
Adds messaging.SubjectSyncStateDelta and a reusable testutil.FakeBus (synchronous
in-process MessagingClient with wildcard matching) for adopter tests.

Component only; service migrations follow in subsequent commits.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* refactor(finetune): back jobs with SyncedMap for cross-replica consistency

FineTuneService kept jobs in a process-local map and, although it wrote them to
Postgres, ListJobs/GetJob never read the store back and the wired natsClient was
never used - so in distributed mode a job created on one replica was invisible to
the others. Replace the map and the dead client with a syncstate.SyncedMap keyed
by job ID, value *schema.FineTuneJob (the exact REST shape, so responses are
unchanged).

- Add a Store adapter (core/services/finetune/syncstore.go) over FineTuneStore,
  plus FineTuneStore.ListAll (global hydrate; per-user List kept) and an
  idempotent Upsert (create-or-update; Create alone fails on dup key).
- Writes go through SyncedMap.Set/Delete (write-through + broadcast); reads use
  List/Get. The on-disk state.json path becomes the standalone Loader, keeping
  single-node restart recovery (stale->stopped / exporting->failed fixups).
- Fold SetNATSClient/SetFineTuneStore into NewFineTuneService; app.go passes the
  distributed NATS client + store when distributed, nil otherwise.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* refactor(agentpool): back agent tasks with SyncedMap for cross-replica consistency

AgentJobService.ListTasks read the process-local tasks map only, while ListJobs
already read through the DB persister + dispatcher NATS - so in distributed mode
a task created on one replica was invisible to the others. Back tasks with a
syncstate.SyncedMap keyed by task ID (value schema.Task, the exact REST shape);
jobs are left untouched.

- Store adapter (task_syncstore.go) over the existing JobPersister
  (LoadTasks/SaveTask/DeleteTask); reads svc.persister/userID live so a persister
  swap needs no rebuild. No new persister methods required.
- Task reads -> SyncedMap.List/Get; create/update -> Set (write-through +
  broadcast); delete -> Delete. The file persister now owns its own task set so
  the write-through path does not re-enter the SyncedMap lock (deadlock guard).
- The distributed NATS client is not available at construction (start() precedes
  initDistributed), so it is injected via SetTaskSyncNATS, which rebuilds the
  still-empty map before Start/hydrate. Wired at the main, restart, and per-user
  (UserServicesManager) distributed sites.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* refactor(quantization): back jobs with SyncedMap + durable QuantStore

QuantizationService kept jobs in a process-local map persisted only to a local
state.json, so in distributed mode jobs were neither visible across replicas nor
durable cluster-wide. Back jobs with a syncstate.SyncedMap keyed by job ID
(value *schema.QuantizationJob, the exact REST shape).

- New distributed.QuantStore (GORM, table quantization_jobs) mirroring
  FineTuneStore: Create/Get/ListAll/Upsert(idempotent)/Delete, registered for
  AutoMigrate via distributed.InitStores (Stores.Quant).
- New adapter (quantization/syncstore.go) over QuantStore implementing
  syncstate.Store, with record<->schema conversion.
- Reads go through List/Get, writes through Set/Delete (write-through +
  broadcast); state.json is kept as the standalone Loader for single-node restart
  recovery (stale-job fixups preserved).
- app.go passes the distributed NATS client + QuantStore when distributed, nil
  otherwise; Start/Close lifecycle mirrors finetune.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* fix(syncstate): annotate gosec G118 false positive on lifeCtx

gosec flagged the WithCancel in Start as "cancellation function not called"
because the returned cancel is stored on the struct rather than called/deferred
in scope. It is invoked in Close (covered by tests), and lifeCtx must outlive
Start to drive the reconnect/reconcile goroutines. Suppress the verified false
positive with a justified #nosec G118.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* test(distributed): e2e two-replica SyncedMap sync over real NATS + Postgres

Adds the real-infrastructure counterpart to the fake-bus unit tests, in the
existing distributed e2e suite (testcontainers NATS + PostgreSQL). Two SyncedMap
instances stand in for two frontend replicas - each with its OWN NATS connection
to a shared server and a SHARED Postgres store (the distributed-mode invariant) -
and assert, over the wire:

- a create on replica A is observed by replica B;
- an update and a delete propagate A -> B (delete prunes, which a reload cannot);
- a late-joining replica recovers a job it never received a delta for, via store
  hydrate on Start (the at-most-once gap a fake bus cannot exercise);
- a local Set is written through to the shared Postgres store.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-06-27 23:23:51 +02:00

106 lines
3.9 KiB
Go

package distributed
import (
"context"
"fmt"
"time"
"github.com/google/uuid"
"github.com/mudler/LocalAI/core/services/advisorylock"
"gorm.io/gorm"
"gorm.io/gorm/clause"
)
// QuantJobRecord tracks quantization jobs in PostgreSQL. The columns mirror the
// API shape (schema.QuantizationJob); the structured Config and ExtraOptions are
// serialized into JSON text columns so a record fully reconstructs the job.
type QuantJobRecord struct {
ID string `gorm:"primaryKey;size:36" json:"id"`
UserID string `gorm:"index;size:36" json:"user_id,omitempty"`
Model string `gorm:"size:255" json:"model"`
Backend string `gorm:"size:64" json:"backend"`
ModelID string `gorm:"size:255" json:"model_id,omitempty"`
QuantizationType string `gorm:"size:32" json:"quantization_type"`
Status string `gorm:"index;size:32;default:queued" json:"status"` // queued, downloading, converting, quantizing, completed, failed, stopped
Message string `gorm:"type:text" json:"message,omitempty"`
OutputDir string `gorm:"size:512" json:"output_dir,omitempty"`
OutputFile string `gorm:"size:512" json:"output_file,omitempty"`
ConfigJSON string `gorm:"column:config;type:text" json:"-"`
ExtraOptsJSON string `gorm:"column:extra_options;type:text" json:"-"`
ImportStatus string `gorm:"size:32" json:"import_status,omitempty"`
ImportMessage string `gorm:"type:text" json:"import_message,omitempty"`
ImportModelName string `gorm:"size:255" json:"import_model_name,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
func (QuantJobRecord) TableName() string { return "quantization_jobs" }
// QuantStore manages quantization job state in PostgreSQL.
type QuantStore struct {
db *gorm.DB
}
// NewQuantStore creates a new QuantStore and auto-migrates.
// Uses a PostgreSQL advisory lock to prevent concurrent migration races
// when multiple instances (frontend + workers) start at the same time.
func NewQuantStore(db *gorm.DB) (*QuantStore, error) {
if err := advisorylock.WithLockCtx(context.Background(), db, advisorylock.KeySchemaMigrate, func() error {
return db.AutoMigrate(&QuantJobRecord{})
}); err != nil {
return nil, fmt.Errorf("migrating quantization_jobs: %w", err)
}
return &QuantStore{db: db}, nil
}
// Create stores a new quantization job.
func (s *QuantStore) Create(job *QuantJobRecord) error {
if job.ID == "" {
job.ID = uuid.New().String()
}
job.CreatedAt = time.Now()
job.UpdatedAt = job.CreatedAt
return s.db.Create(job).Error
}
// Get retrieves a quantization job by ID.
func (s *QuantStore) Get(id string) (*QuantJobRecord, error) {
var job QuantJobRecord
if err := s.db.First(&job, "id = ?", id).Error; err != nil {
return nil, err
}
return &job, nil
}
// ListAll returns every quantization job across all users. The SyncedMap that
// backs QuantizationService is a single global map (the REST API filters by user
// at read time), so hydrate needs the full set.
func (s *QuantStore) ListAll() ([]QuantJobRecord, error) {
var jobs []QuantJobRecord
return jobs, s.db.Order("created_at DESC").Find(&jobs).Error
}
// Upsert idempotently inserts or fully replaces a job row by primary key. The
// SyncedMap write-through path issues a single Set per mutation regardless of
// whether the job already exists, so it needs one create-or-update primitive
// (Create alone fails on a duplicate key).
func (s *QuantStore) Upsert(job *QuantJobRecord) error {
if job.ID == "" {
job.ID = uuid.New().String()
}
now := time.Now()
if job.CreatedAt.IsZero() {
job.CreatedAt = now
}
job.UpdatedAt = now
return s.db.Clauses(clause.OnConflict{
Columns: []clause.Column{{Name: "id"}},
UpdateAll: true,
}).Create(job).Error
}
// Delete removes a quantization job.
func (s *QuantStore) Delete(id string) error {
return s.db.Where("id = ?", id).Delete(&QuantJobRecord{}).Error
}