docs: finalize documentation for Go migration

Updated README, architecture, and TODO to reflect full feature parity, system metrics, and registry integration.

BACKEND_ARCHITECTURE.md

@@ -9,6 +9,7 @@ The LLM Proxy backend is implemented in Go, focusing on high performance, clear
 - **Database:** [sqlx](https://github.com/jmoiron/sqlx) - Lightweight wrapper for standard `database/sql`.
 - **SQLite Driver:** [modernc.org/sqlite](https://modernc.org/sqlite) - CGO-free SQLite implementation for ease of cross-compilation.
 - **Config:** [Viper](https://github.com/spf13/viper) - Robust configuration management supporting environment variables and files.
+- **Metrics:** [gopsutil](https://github.com/shirou/gopsutil) - System-level resource monitoring.
 
 ## Project Structure
 
@@ -22,40 +23,40 @@ The LLM Proxy backend is implemented in Go, focusing on high performance, clear
 │   ├── models/             # Unified request/response structs
 │   ├── providers/          # LLM provider implementations (OpenAI, Gemini, etc.)
 │   ├── server/             # HTTP server, dashboard handlers, and WebSocket hub
-│   └── utils/              # Common utilities (multimodal, etc.)
+│   └── utils/              # Common utilities (registry, pricing, etc.)
 └── static/                 # Frontend assets (served by the backend)
 ```
 
 ## Key Components
 
 ### 1. Provider Interface (`internal/providers/provider.go`)
-Standardized interface for all LLM backends:
-```go
-type Provider interface {
-	Name() string
-	ChatCompletion(ctx context.Context, req *models.UnifiedRequest) (*models.ChatCompletionResponse, error)
-	ChatCompletionStream(ctx context.Context, req *models.UnifiedRequest) (<-chan *models.ChatCompletionStreamResponse, error)
-}
-```
+Standardized interface for all LLM backends. Implementations handle mapping between the unified format and provider-specific APIs (OpenAI, Gemini, DeepSeek, Grok).
 
-### 2. Asynchronous Logging (`internal/server/logging.go`)
+### 2. Model Registry & Pricing (`internal/utils/registry.go`)
+Integrates with `models.dev/api.json` to provide real-time model metadata and pricing. 
+- **Fuzzy Matching:** Supports matching versioned model IDs (e.g., `gpt-4o-2024-08-06`) to base registry entries.
+- **Automatic Refreshes:** The registry is fetched at startup and refreshed every 24 hours via a background goroutine.
+
+### 3. Asynchronous Logging (`internal/server/logging.go`)
 Uses a buffered channel and background worker to log every request to SQLite without blocking the client response. It also broadcasts logs to the WebSocket hub for real-time dashboard updates.
 
-### 3. Session Management (`internal/server/sessions.go`)
-Implements HMAC-SHA256 signed tokens for dashboard authentication. Sessions are stored in-memory with configurable TTL.
+### 4. Session Management (`internal/server/sessions.go`)
+Implements HMAC-SHA256 signed tokens for dashboard authentication. Tokens secure the management interface while standard Bearer tokens are used for LLM API access.
 
-### 4. WebSocket Hub (`internal/server/websocket.go`)
-A centralized hub for managing WebSocket connections, allowing real-time broadcast of system events and request logs to the dashboard.
+### 5. WebSocket Hub (`internal/server/websocket.go`)
+A centralized hub for managing WebSocket connections, allowing real-time broadcast of system events, system metrics, and request logs to the dashboard.
 
 ## Concurrency Model
 
 Go's goroutines and channels are used extensively:
-- **Streaming:** Each streaming request uses a goroutine to read and parse the provider's response, feeding chunks into a channel.
-- **Logging:** A single background worker processes the `logChan` to perform database writes.
+- **Streaming:** Each streaming request uses a goroutine to read and parse the provider's response, feeding chunks into a channel for SSE delivery.
+- **Logging:** A single background worker processes the `logChan` to perform serial database writes.
 - **WebSocket:** The `Hub` runs in a dedicated goroutine, handling registration and broadcasting.
+- **Maintenance:** Background tasks handle registry refreshes and status monitoring.
 
 ## Security
 
-- **Encryption Key:** A mandatory 32-byte key is used for both session signing and encryption of sensitive data in the database.
-- **Auth Middleware:** Verifies client API keys against the database before proxying requests to LLM providers.
+- **Encryption Key:** A mandatory 32-byte key is used for both session signing and encryption of sensitive data.
+- **Auth Middleware:** Scoped to `/v1` routes to verify client API keys against the database.
 - **Bcrypt:** Passwords for dashboard users are hashed using Bcrypt with a work factor of 12.
+- **Database Hardening:** Automatic migrations ensure the schema is always current with the code.