fix: add provider warmup to prevent cold-start timeout on first channel message

The first API request after daemon startup consistently timed out (120s)
when using channels (Telegram, Discord, etc.), requiring a retry before
succeeding. This happened because the reqwest HTTP client's connection
pool was cold — no TLS handshake, DNS resolution, or HTTP/2 negotiation
had occurred yet.

The fix adds a `warmup()` method to the Provider trait that establishes
the connection pool on startup by hitting a lightweight endpoint
(`/api/v1/auth/key` for OpenRouter). The channel server calls this
immediately after creating the provider, before entering the message
processing loop.

Tested on Raspberry Pi 5 (aarch64) with OpenRouter + DeepSeek v3.2 via
Telegram channel. Before: first message took 2-7 minutes (120s timeout +
retries). After: first message responds in <30s with no retries.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/providers/reliable.rs

@@ -25,6 +25,14 @@ impl ReliableProvider {
 
 #[async_trait]
 impl Provider for ReliableProvider {
+    async fn warmup(&self) -> anyhow::Result<()> {
+        if let Some((name, provider)) = self.providers.first() {
+            tracing::info!(provider = name, "Warming up provider connection pool");
+            provider.warmup().await?;
+        }
+        Ok(())
+    }
+
     async fn chat_with_system(
         &self,
         system_prompt: Option<&str>,