Files
LocalAI/core/services/modeladmin/state.go
T
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

111 lines
3.2 KiB
Go

package modeladmin
import (
"context"
"fmt"
"os"
"gopkg.in/yaml.v3"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/pkg/utils"
)
// ToggleResult is shared by ToggleState and TogglePinned.
type ToggleResult struct {
Filename string
Action Action
ConfigRevision string
PendingCleanup int
}
// ToggleState enables or disables an installed model. action must be
// ActionEnable or ActionDisable. The revision lifecycle quarantines existing
// replicas before cleanup when the state changes.
//
// The on-disk YAML is mutated as a generic map so unrelated fields are
// preserved verbatim; we only set or remove the `disabled` key.
func (s *ConfigService) ToggleState(ctx context.Context, name string, action Action) (*ToggleResult, error) {
var result *ToggleResult
err := s.Loader.WithModelConfigMutation(func() error {
var err error
result, err = s.toggleState(ctx, name, action)
return err
})
return result, err
}
func (s *ConfigService) toggleState(ctx context.Context, name string, action Action) (*ToggleResult, error) {
if name == "" {
return nil, ErrNameRequired
}
if !action.Valid(ActionEnable, ActionDisable) {
return nil, fmt.Errorf("%w: must be %q or %q, got %q", ErrBadAction, ActionEnable, ActionDisable, action)
}
cfg, exists := s.Loader.GetModelConfig(name)
if !exists {
return nil, ErrNotFound
}
configPath := cfg.GetModelConfigFile()
if configPath == "" {
return nil, ErrConfigFileMissing
}
if err := utils.VerifyPath(configPath, s.modelsPath()); err != nil {
return nil, fmt.Errorf("%w: %v", ErrPathNotTrusted, err)
}
var result *ToggleResult
err := s.withMutationRollback([]string{configPath}, func() error {
if err := mutateYAMLBoolFlag(configPath, "disabled", action == ActionDisable); err != nil {
return err
}
if err := s.Loader.LoadModelConfigsFromPath(s.modelsPath(), s.AppConfig.ToConfigLoaderOptions()...); err != nil {
return fmt.Errorf("reload configs: %w", err)
}
loaded, ok := s.Loader.GetModelConfig(name)
if !ok {
return fmt.Errorf("reload configs: model %q missing", name)
}
revision, err := config.ModelConfigRevision(&loaded)
if err != nil {
return fmt.Errorf("compute config revision: %w", err)
}
pending, err := s.applyRevision(ctx, name, name, revision, action == ActionDisable)
if err != nil {
return err
}
result = &ToggleResult{Filename: configPath, Action: action, ConfigRevision: revision, PendingCleanup: pending}
return nil
})
return result, err
}
// mutateYAMLBoolFlag is a small helper shared by ToggleState and
// TogglePinned: read the file as a generic map, set or remove a bool key,
// write back. Setting `set=false` removes the key for a clean YAML.
func mutateYAMLBoolFlag(path, key string, set bool) error {
data, err := os.ReadFile(path)
if err != nil {
return fmt.Errorf("read config: %w", err)
}
var m map[string]any
if err := yaml.Unmarshal(data, &m); err != nil {
return fmt.Errorf("parse config: %w", err)
}
if m == nil {
m = map[string]any{}
}
if set {
m[key] = true
} else {
delete(m, key)
}
out, err := yaml.Marshal(m)
if err != nil {
return fmt.Errorf("marshal config: %w", err)
}
if err := writeFileAtomic(path, out, 0644); err != nil {
return fmt.Errorf("write config: %w", err)
}
return nil
}