Make LanguageModel::use_any_tool return a stream of chunks (#16262)

This PR is a refactor to pave the way for allowing the user to view and
edit workflow step resolutions. I've made tool calls work more like
normal streaming completions for all providers. The `use_any_tool`
method returns a stream of strings (which contain chunks of JSON). I've
also done some minor cleanup of language model providers in general,
removing the duplication around handling streaming responses.

Release Notes:

- N/A

crates/language_model/src/provider/google.rs

@@ -302,7 +302,7 @@ impl LanguageModel for GoogleLanguageModel {
         _description: String,
         _schema: serde_json::Value,
         _cx: &AsyncAppContext,
-    ) -> BoxFuture<'static, Result<serde_json::Value>> {
+    ) -> BoxFuture<'static, Result<futures::stream::BoxStream<'static, Result<String>>>> {
         future::ready(Err(anyhow!("not implemented"))).boxed()
     }
 }