Initial implementation of SwiftDBAI

Chat with any SQLite database using natural language. Built on
AnyLanguageModel (HuggingFace) for LLM-agnostic provider support
and GRDB for SQLite access.

Core features:
- Auto schema introspection from sqlite_master (zero config)
- NL → SQL generation via any AnyLanguageModel provider
- Three rendering modes: text summary, data table, Swift Charts
- Drop-in DataChatView (SwiftUI) and headless ChatEngine
- Operation allowlist with read-only default
- Mutation policy with per-table control
- ToolExecutionDelegate for destructive operation confirmation
- Multi-turn conversation context
- 352 tests across 24 suites, all passing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Tests/SwiftDBAITests/Helpers/MockLanguageModel.swift

@@ -0,0 +1,49 @@
+// MockLanguageModel.swift
+// SwiftDBAI Tests
+//
+// A mock LanguageModel for unit tests that returns canned responses.
+
+import AnyLanguageModel
+import Foundation
+
+/// A mock language model that returns a configurable canned response.
+///
+/// Used in tests to avoid hitting a real LLM provider.
+struct MockLanguageModel: LanguageModel {
+    typealias UnavailableReason = Never
+
+    /// The text the mock will return from `respond(...)`.
+    let responseText: String
+
+    init(responseText: String = "Mock summary response.") {
+        self.responseText = responseText
+    }
+
+    func respond<Content>(
+        within session: LanguageModelSession,
+        to prompt: Prompt,
+        generating type: Content.Type,
+        includeSchemaInPrompt: Bool,
+        options: GenerationOptions
+    ) async throws -> LanguageModelSession.Response<Content> where Content: Generable {
+        let rawContent = GeneratedContent(kind: .string(responseText))
+        let content = try Content(rawContent)
+        return LanguageModelSession.Response(
+            content: content,
+            rawContent: rawContent,
+            transcriptEntries: [][...]
+        )
+    }
+
+    func streamResponse<Content>(
+        within session: LanguageModelSession,
+        to prompt: Prompt,
+        generating type: Content.Type,
+        includeSchemaInPrompt: Bool,
+        options: GenerationOptions
+    ) -> sending LanguageModelSession.ResponseStream<Content> where Content: Generable {
+        let rawContent = GeneratedContent(kind: .string(responseText))
+        let content = try! Content(rawContent)
+        return LanguageModelSession.ResponseStream(content: content, rawContent: rawContent)
+    }
+}