ai: extract ResolvedBackend, remove ~480 lines of duplicated dispatch

Replace 5 copies of the ~80-line backend resolution pattern with a
single InsightGenerator::resolve_backend() builder that returns a
ResolvedBackend (chat + local clients, BackendKind enum, images_inline
flag). Tool dispatch now takes &ResolvedBackend instead of
&OllamaClient + model + backend strings.

Remove duplicated ollama/openrouter/llamacpp fields from
InsightChatService — InsightGenerator owns them and resolve_backend
uses them. Delete build_chat_clients (replaced by resolve_backend).

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

src/state.rs

@@ -290,9 +290,6 @@ impl Default for AppState {
             Arc::new(tokio::sync::Mutex::new(std::collections::HashMap::new()));
         let insight_chat = Arc::new(InsightChatService::new(
             Arc::new(insight_generator.clone()),
-            ollama.clone(),
-            openrouter.clone(),
-            llamacpp.clone(),
             insight_dao.clone(),
             chat_locks,
         ));
@@ -470,9 +467,6 @@ impl AppState {
             Arc::new(tokio::sync::Mutex::new(std::collections::HashMap::new()));
         let insight_chat = Arc::new(InsightChatService::new(
             Arc::new(insight_generator.clone()),
-            ollama.clone(),
-            None,
-            None,
             insight_dao.clone(),
             chat_locks,
         ));