Refactor LLM config into top-level settings

Replace the monolithic agents config with a cleaner structure:
- llm: holds provider credentials and default model settings
- probo-agent: LLM overrides for the probo agent
- evidence-describer: worker config (interval, stale-after,
  max-concurrency) alongside LLM overrides

This makes worker tuning configurable via YAML and env vars
instead of being hardcoded in Go, and separates provider
credentials from per-consumer model settings.

Signed-off-by: Bryan Frimin <bryan@getprobo.com>

cfg/dev.yaml

@@ -85,17 +85,22 @@ probod:
     slack:
       sender-interval: 60
 
-  agents:
+  llm:
     providers:
       openai:
-        type: "openai"
+        type: openai
         api-key: "thisisnotasecret"
-    default:
-      provider: "openai"
-      model-name: "gpt-4o"
+    defaults:
+      provider: openai
+      model-name: gpt-4o
       temperature: 0.1
       max-tokens: 4096
 
+  evidence-describer:
+    interval: 10
+    stale-after: 300
+    max-concurrency: 10
+
   custom-domains:
     renewal-interval: 3600
     provision-interval: 30