refactor: introduce LlmClient trait (no-op)

Preparation for a second LLM backend (OpenRouter) and hybrid vision-local /
chat-remote mode. Shared wire types (ChatMessage, Tool, ToolCall, etc.) move
into a new src/ai/llm_client.rs and are re-exported from ollama.rs so
existing imports keep working. OllamaClient now implements LlmClient.

No behavior change; callers still hold the concrete OllamaClient. Caller
migration to Arc<dyn LlmClient> is deferred to the PR that wires hybrid
backend routing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/ai/mod.rs

@@ -1,6 +1,7 @@
 pub mod daily_summary_job;
 pub mod handlers;
 pub mod insight_generator;
+pub mod llm_client;
 pub mod ollama;
 pub mod sms_client;
 
@@ -13,5 +14,9 @@ pub use handlers::{
     get_insight_handler, rate_insight_handler,
 };
 pub use insight_generator::InsightGenerator;
-pub use ollama::{ModelCapabilities, OllamaClient};
+#[allow(unused_imports)]
+pub use llm_client::{
+    ChatMessage, LlmClient, ModelCapabilities, Tool, ToolCall, ToolCallFunction, ToolFunction,
+};
+pub use ollama::OllamaClient;
 pub use sms_client::{SmsApiClient, SmsMessage};