Make language model deserialization more resilient (#31311)

This expands our deserialization of JSON from models to be more tolerant
of different variations that the model may send, including
capitalization, wrapping things in objects vs. being plain strings, etc.

Also when deserialization fails, it reports the entire error in the JSON
so we can see what failed to deserialize. (Previously these errors were
very unhelpful at diagnosing the problem.)

Finally, also removes the `WrappedText` variant since the custom
deserializer just turns that style of JSON into a normal `Text` variant.

Release Notes:

- N/A

crates/eval/src/instance.rs

@@ -9,7 +9,7 @@ use handlebars::Handlebars;
 use language::{Buffer, DiagnosticSeverity, OffsetRangeExt as _};
 use language_model::{
     LanguageModel, LanguageModelCompletionEvent, LanguageModelRequest, LanguageModelRequestMessage,
-    LanguageModelToolResultContent, MessageContent, Role, TokenUsage, WrappedTextContent,
+    LanguageModelToolResultContent, MessageContent, Role, TokenUsage,
 };
 use project::lsp_store::OpenLspBufferHandle;
 use project::{DiagnosticSummary, Project, ProjectPath};
@@ -967,11 +967,7 @@ impl RequestMarkdown {
                         }
 
                         match &tool_result.content {
-                            LanguageModelToolResultContent::Text(text)
-                            | LanguageModelToolResultContent::WrappedText(WrappedTextContent {
-                                text,
-                                ..
-                            }) => {
+                            LanguageModelToolResultContent::Text(text) => {
                                 writeln!(messages, "{text}\n").ok();
                             }
                             LanguageModelToolResultContent::Image(image) => {