@@ -13,33 +13,48 @@ Lightspeed Core Stack (LCS) is an AI-powered assistant built on FastAPI that pro
1313## Code Architecture & Patterns
1414
1515### Project Structure
16+
1617```
1718src/
18- ├── app/ # FastAPI application
19- │ ├── endpoints/ # REST API endpoints
20- │ └── main.py # Application entry point
21- ├── a2a_storage/ # A2A protocol persistent storage
22- │ ├── context_store.py # Abstract base class for context stores
19+ ├── app/ # FastAPI application
20+ │ ├── endpoints/ # REST API endpoints
21+ │ └── main.py # Application entry point
22+ ├── a2a_storage/ # A2A protocol persistent storage
23+ │ ├── context_store.py # Abstract base class for context stores
2324│ ├── in_memory_context_store.py # In-memory implementation
2425│ ├── sqlite_context_store.py # SQLite implementation
2526│ ├── postgres_context_store.py # PostgreSQL implementation
2627│ └── storage_factory.py # Factory for creating stores
27- ├── authentication/ # Authentication modules (k8s, jwk, noop, rh-identity)
28- ├── authorization/ # Authorization middleware & resolvers
29- ├── cache/ # Conversation cache implementations
30- ├── quota/ # Quota limiter and token usage tracking
31- ├── metrics/ # Prometheus metrics
32- ├── runners/ # Agent runners
33- ├── models/ # Pydantic models
34- │ ├── api/
35- │ │ ├── requests/ # REST API request models
36- │ │ └── responses/ # HTTP response models
37- │ ├── common/ # Shared cross-layer models
38- │ └── database/ # Database models
39- ├── utils/ # Utility functions
40- ├── client.py # Llama Stack client wrapper (Singleton)
41- ├── configuration.py # Config management (Singleton)
42- └── constants.py # Shared constants
28+ ├── authentication/ # Authentication modules (k8s, jwk, noop, rh-identity)
29+ ├── authorization/ # Authorization middleware & resolvers
30+ ├── cache/ # Conversation cache implementations
31+ ├── data/ # Built-in default Llama Stack baseline for unified-mode synthesis
32+ ├── quota/ # Quota limiter and token usage tracking
33+ ├── metrics/ # Prometheus metrics
34+ ├── runners/ # Runners for various LCore subsystems
35+ ├── models/ # Pydantic models
36+ │ ├── api/ # REST API models
37+ │ │ ├── requests/ # REST API request models
38+ │ │ └── responses/ # HTTP response models
39+ │ │ ├── error/ # Error responses
40+ │ │ └── successful/ # Successful responses
41+ │ ├── common/ # Shared cross-layer models
42+ │ │ ├── agents/ # Streaming payload models and event type exports
43+ │ │ └── responses/ # Shared models for the OpenAI-compatible Responses API pipeline
44+ │ └── database/ # Database models
45+ ├── observability/ # Observability module for telemetry and event collection
46+ │ └── formats/ # Event format builders for Splunk telemetry
47+ ├── pydantic_ai_lightspeed/ # Pydantic AI integrations/extensions for Lightspeed Core Stack
48+ │ ├── capabilities/ # Pluggable capabilities for pydantic-ai agents in Lightspeed
49+ │ │ ├── question_validity/ # Question validity capability for agent input validation
50+ │ │ └── redaction/ # PII redaction capability for Pydantic AI agents
51+ │ └── llamastack/ # Pydantic AI provider for Llama Stack
52+ ├── telemetry/ # Telemetry module for configuration snapshot collection
53+ ├── utils/ # Utility functions
54+ │ └── agents # Agent streaming and non streaming helpers
55+ ├── client.py # Llama Stack client wrapper (Singleton)
56+ ├── configuration.py # Config management (Singleton)
57+ └── constants.py # Shared (final) constants
4358```
4459
4560### Coding Standards
0 commit comments