docs: updating guides to provide more clarity around moderator (#628)

docs/configuration.md

@@ -40,6 +40,9 @@ Rules designed to control or manage the output of the model. Moderators that cur
 
 - `passive`: does not actively intervene in every response
 - `truncate`: truncates the first contexts when the contexts exceed the max token size
+- `synopsis`: instead of truncating, it uses LLMs to summarize and condense context dynamically, keeping relevant information while staying under the token limit.
+
+> **Important:** `synopsis` only works when the `synopsis` toolkit is enabled. Be sure to update your [`profile.yml` configurations](https://block.github.io/goose/guidance/getting-started.html#configuring-goose-with-the-profilesyaml-file) to enable both.
 
 
 #### toolkits

docs/plugins/providers.md

@@ -23,7 +23,12 @@ default:
   provider: anthropic
   processor: claude-3-5-sonnet-20241022
   accelerator: claude-3-5-sonnet-20241022
+  moderator: synopsis
+  toolkits:
+  - name: synopsis
+    requires: {}
 ```
+> **Important** Anthropic performs the best when both the `synopsis` toolkit and moderator are enabled.
 
 ### Azure
 
@@ -68,8 +73,12 @@ default:
   provider: google
   processor: gemini-1.5-flash
   accelerator: gemini-1.5-flash
+  moderator: truncate
+  toolkits:
+  - name: developer
+    requires: {}
 ```
-
+> **Important** Gemini performs the best when both the `developer` toolkit and `truncate` moderator are enabled.
 ### Ollama
 
 For Ollama, refer to the setup process on [Ollama's site](https://ollama.com/) for obtaining necessary credentials. Make sure your environment has all the required tokens set up.