llm: route every LLM caller through a shared backend client

Replaces the per-plugin Ollama HTTP calls with internal/llm, which picks a
backend from the environment (vLLM or Ollama) behind one Chat interface, plus
internal/plugin/llm_client.go as the plugin-facing wrapper.

Startup now logs llm_backend/llm_endpoint/llm_model instead of the two
OLLAMA_* vars, which no longer describe where inference actually goes.

These files were already running in prod from the vLLM migration but had never
been committed; this is that live state, byte-for-byte.

internal/llm/ping.go

@@ -0,0 +1,29 @@
+package llm
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"time"
+)
+
+// pingTimeout keeps a liveness probe short — /botinfo renders synchronously and
+// a hung endpoint must not hold the reply.
+const pingTimeout = 5 * time.Second
+
+func getJSON(ctx context.Context, url string, out any) error {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return err
+	}
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("HTTP %d", resp.StatusCode)
+	}
+	return json.NewDecoder(resp.Body).Decode(out)
+}