mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
b1a99436c7
Adds a whitelabeling feature so an operator can replace the LocalAI
instance name, tagline, square logo, horizontal logo, and favicon from
the admin Settings page. Defaults fall back to the bundled assets so
existing installs are unaffected.
The public GET /api/branding endpoint is reachable pre-auth so the
login screen can render the configured branding before sign-in.
Mutating routes (POST/DELETE /api/branding/asset/:kind) remain
admin-only. Text fields (instance_name, instance_tagline) ride the
existing /api/settings flow; binary assets get a dedicated multipart
upload route that persists files under DynamicConfigsDir/branding/.
To prevent the Settings page's stale local state from clobbering an
upload on save, UpdateSettingsEndpoint preserves whatever the on-disk
asset filename fields are regardless of the body — /api/branding/asset/*
are the sole writers for those fields.
The MCP catalog gains get_branding and set_branding tools (text fields
only; file upload stays UI-only) plus a configure_branding skill prompt.
While wiring this up, the same restart-loss class of bug surfaced for
several existing fields whose RuntimeSettings entries were never read
by the startup loader. Fix loadRuntimeSettingsFromFile() to load:
- branding (instance_name, instance_tagline, *_file basenames)
- auto_upgrade_backends, prefer_development_backends
- localai_assistant_enabled
- open_responses_store_ttl
- the 7 existing AgentPool fields (enabled, default/embedding model,
chunking sizes, enable_logs, collection_db_path)
Also exposes 3 new AgentPool runtime settings (vector_engine,
database_url, agent_hub_url) via /api/settings + the Settings UI, with
the same load-on-startup wiring. The file watcher's manual-edit path
is intentionally not changed — the in-process API endpoints already
update appConfig directly, so the watcher is redundant for supported
flows and a separate refactor for everything else.
15 TDD specs cover the loader behaviour (1 branding + 11 adjacent + 3
new agent-pool); 2 specs cover the persistence helpers and the
clobber-prevention contract.
Assisted-by: claude-code:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
93 lines
5.4 KiB
Go
93 lines
5.4 KiB
Go
package config
|
|
|
|
// RuntimeSettings represents runtime configuration that can be changed dynamically.
|
|
// This struct is used for:
|
|
// - API responses (GET /api/settings)
|
|
// - API requests (POST /api/settings)
|
|
// - Persisting to runtime_settings.json
|
|
// - Loading from runtime_settings.json on startup
|
|
//
|
|
// All fields are pointers to distinguish between "not set" and "set to zero/false value".
|
|
type RuntimeSettings struct {
|
|
// Watchdog settings
|
|
WatchdogEnabled *bool `json:"watchdog_enabled,omitempty"`
|
|
WatchdogIdleEnabled *bool `json:"watchdog_idle_enabled,omitempty"`
|
|
WatchdogBusyEnabled *bool `json:"watchdog_busy_enabled,omitempty"`
|
|
WatchdogIdleTimeout *string `json:"watchdog_idle_timeout,omitempty"`
|
|
WatchdogBusyTimeout *string `json:"watchdog_busy_timeout,omitempty"`
|
|
WatchdogInterval *string `json:"watchdog_interval,omitempty"` // Interval between watchdog checks (e.g., 2s, 30s)
|
|
|
|
// Backend management
|
|
SingleBackend *bool `json:"single_backend,omitempty"` // Deprecated: use MaxActiveBackends = 1 instead
|
|
MaxActiveBackends *int `json:"max_active_backends,omitempty"` // Maximum number of active backends (0 = unlimited, 1 = single backend mode)
|
|
AutoUpgradeBackends *bool `json:"auto_upgrade_backends,omitempty"` // Automatically upgrade backends when new versions are detected
|
|
PreferDevelopmentBackends *bool `json:"prefer_development_backends,omitempty"` // Prefer development backend versions by default in UI
|
|
// Memory Reclaimer settings (works with GPU if available, otherwise RAM)
|
|
MemoryReclaimerEnabled *bool `json:"memory_reclaimer_enabled,omitempty"` // Enable memory threshold monitoring
|
|
MemoryReclaimerThreshold *float64 `json:"memory_reclaimer_threshold,omitempty"` // Threshold 0.0-1.0 (e.g., 0.95 = 95%)
|
|
|
|
// Eviction settings
|
|
ForceEvictionWhenBusy *bool `json:"force_eviction_when_busy,omitempty"` // Force eviction even when models have active API calls (default: false for safety)
|
|
LRUEvictionMaxRetries *int `json:"lru_eviction_max_retries,omitempty"` // Maximum number of retries when waiting for busy models to become idle (default: 30)
|
|
LRUEvictionRetryInterval *string `json:"lru_eviction_retry_interval,omitempty"` // Interval between retries when waiting for busy models (e.g., 1s, 2s) (default: 1s)
|
|
|
|
// Performance settings
|
|
Threads *int `json:"threads,omitempty"`
|
|
ContextSize *int `json:"context_size,omitempty"`
|
|
F16 *bool `json:"f16,omitempty"`
|
|
Debug *bool `json:"debug,omitempty"`
|
|
EnableTracing *bool `json:"enable_tracing,omitempty"`
|
|
TracingMaxItems *int `json:"tracing_max_items,omitempty"`
|
|
EnableBackendLogging *bool `json:"enable_backend_logging,omitempty"`
|
|
|
|
// Security/CORS settings
|
|
CORS *bool `json:"cors,omitempty"`
|
|
CSRF *bool `json:"csrf,omitempty"`
|
|
CORSAllowOrigins *string `json:"cors_allow_origins,omitempty"`
|
|
|
|
// P2P settings
|
|
P2PToken *string `json:"p2p_token,omitempty"`
|
|
P2PNetworkID *string `json:"p2p_network_id,omitempty"`
|
|
Federated *bool `json:"federated,omitempty"`
|
|
|
|
// Gallery settings
|
|
Galleries *[]Gallery `json:"galleries,omitempty"`
|
|
BackendGalleries *[]Gallery `json:"backend_galleries,omitempty"`
|
|
AutoloadGalleries *bool `json:"autoload_galleries,omitempty"`
|
|
AutoloadBackendGalleries *bool `json:"autoload_backend_galleries,omitempty"`
|
|
|
|
// API keys - No omitempty as we need to save empty arrays to clear keys
|
|
ApiKeys *[]string `json:"api_keys"`
|
|
|
|
// Agent settings
|
|
AgentJobRetentionDays *int `json:"agent_job_retention_days,omitempty"`
|
|
|
|
// Open Responses settings
|
|
OpenResponsesStoreTTL *string `json:"open_responses_store_ttl,omitempty"` // TTL for stored responses (e.g., "1h", "30m", "0" = no expiration)
|
|
|
|
// Agent Pool settings
|
|
AgentPoolEnabled *bool `json:"agent_pool_enabled,omitempty"`
|
|
AgentPoolDefaultModel *string `json:"agent_pool_default_model,omitempty"`
|
|
AgentPoolEmbeddingModel *string `json:"agent_pool_embedding_model,omitempty"`
|
|
AgentPoolMaxChunkingSize *int `json:"agent_pool_max_chunking_size,omitempty"`
|
|
AgentPoolChunkOverlap *int `json:"agent_pool_chunk_overlap,omitempty"`
|
|
AgentPoolEnableLogs *bool `json:"agent_pool_enable_logs,omitempty"`
|
|
AgentPoolCollectionDBPath *string `json:"agent_pool_collection_db_path,omitempty"`
|
|
AgentPoolVectorEngine *string `json:"agent_pool_vector_engine,omitempty"` // chromem | postgres
|
|
AgentPoolDatabaseURL *string `json:"agent_pool_database_url,omitempty"` // PostgreSQL DSN when vector engine is postgres
|
|
AgentPoolAgentHubURL *string `json:"agent_pool_agent_hub_url,omitempty"` // override the agenthub.localai.io endpoint
|
|
|
|
// LocalAI Assistant settings — read live by the chat handler at request
|
|
// entry, so flipping the toggle takes effect on the next request.
|
|
LocalAIAssistantEnabled *bool `json:"localai_assistant_enabled,omitempty"` // negation of DisableLocalAIAssistant for UI clarity
|
|
|
|
// Branding / whitelabeling. Text fields are user-facing; *File fields hold
|
|
// just the basename of an uploaded asset under {DynamicConfigsDir}/branding/.
|
|
// All optional — empty values fall back to bundled LocalAI defaults.
|
|
InstanceName *string `json:"instance_name,omitempty"`
|
|
InstanceTagline *string `json:"instance_tagline,omitempty"`
|
|
LogoFile *string `json:"logo_file,omitempty"`
|
|
LogoHorizontalFile *string `json:"logo_horizontal_file,omitempty"`
|
|
FaviconFile *string `json:"favicon_file,omitempty"`
|
|
}
|