feat: add conversation persistence and context management layer

- SQLAlchemy async database layer (SQLite dev, PostgreSQL prod)
- Conversation and Message models with UUID primary keys
- Token counting utilities using litellm
- Context summarization at 80% token threshold
- REST API endpoints for multi-turn conversations
- 19 conversation tests, 6 token tests (176 total passing)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

webber-api/src/shared/config.py

@@ -80,9 +80,15 @@ class Settings(BaseSettings):
     sandbox_enabled: bool = True
     allowed_paths: list[str] | None = None
 
-    # Sessions
+    # Database
+    database_url: str = "sqlite+aiosqlite:///./webber.db"
+
+    # Sessions & Context
     session_ttl_hours: int = 24
     max_context_tokens: int = 128000
+    summarization_threshold: float = 0.8  # Summarize at 80% of max tokens
+    summarization_target_tokens: int = 500  # Target summary size
+    keep_recent_messages: int = 6  # Messages to keep unsummarized (3 turns)
 
     model_config = SettingsConfigDict(
         env_file=".env",