Core Extension Features01
1. Container-Managed AI Service Graph
On Register(app) the extension registers constructors for:
aisdk.LLMManageraisdk.StateStoreaisdk.VectorStore*AgentFactory*AgentManager
All are registered eagerly, so constructor problems surface during startup instead of at first request.
2. Smart Fallbacks for Stores
State store:
tries existing DI service (
stateStore)else builds from config (
memory,postgres,redis)on failure falls back to in-memory store with
24hTTL
Vector store:
tries existing DI service (
vectorStore)else builds from config
on failure falls back to in-memory vector store
3. Agent Template System (8 Built-In Types)
Each template includes a system prompt and three tools.
| Type | Primary Scope |
cache_optimizer | Cache hit/miss and eviction strategy |
scheduler | Scheduling and resource allocation |
anomaly_detector | Statistical anomaly analysis |
load_balancer | Traffic and capacity balancing |
security_monitor | Security anomaly and threat response |
resource_manager | CPU, memory, and allocation optimization |
predictor | Forecasting and trend prediction |
optimizer | General system optimization |
4. REST Controller for Agent Management
AgentController exposes:
CRUD for dynamic agents
template listing
execution/chat endpoints
Routes are explicit and only exist if you mount the controller.
Optional Feature Sets in Subpackages02
These are available in the module, but not automatically bootstrapped by ai.Extension:
inference: high-throughput inference pipeline, batching, caching, scalingtraining: model trainer, dataset manager, pipeline managermiddleware: intelligent rate limit, anomaly detection, personalization, response optimization, adaptive load balancing, security scannermonitoring: health monitor, metrics collector, alert manager, dashboard
Important Implementation Limits (Current)03
LLMConfiguration.Providersis not auto-registered intoLLMManager; provider registration is manual.CreateVectorStoreonly fully supportsmemorytoday.postgres,pinecone, andweaviatereturn not-implemented errors.extension-level constructor then falls back to memory vector store.
Training DI services are registered based on
Training.Enabled.EnableTrainingin top-level config is not the registration switch by itself.Agent definitions are stored in-memory by
AgentManager.
Operational Guidance04
Use type-based injection for app services (
forge.InjectType[T]) and only use key aliases for compatibility.Treat vector persistence as memory-only unless you deliberately replace the constructor with your own implementation.
If you need durability for agent definitions (not only conversation state), persist your own metadata outside
AgentManager.