fix(chat): an edit after a broken edit call no longer fails, found with Opus 5.5

- Claude Opus 5.5 sent an edit with invalid JSON, then the same edit
  again. The first call's streamed preview was never undone: its input
  has no operations, and the undo sat behind that check. The second edit
  then started from the preview, failed on a duplicate id, and the model
  had to try a third time. The undo now runs first, and an edit that
  starts in the same render uses the undone diagram.
- The SDK passes an invalid tool call's error as a string, which was
  wrapped as a provider error. streamErrorText keeps it as the text the
  model reads.
- Bedrock's "on-demand throughput isn't supported" gets the model id hint.
- The thinking header uses the page language ("Thought for 1 second" in
  English), from the dictionary entries that were already there.

app/api/chat/route.ts

@@ -38,7 +38,7 @@ import {
     setTraceOutput,
     wrapWithObserve,
 } from "@/lib/langfuse"
-import { classifyLLMError, isToolCallError } from "@/lib/llm-errors"
+import { classifyLLMError, streamErrorText } from "@/lib/llm-errors"
 import {
     resolveMaxOutputTokens,
     withOutputTokenLimitFallback,
@@ -724,12 +724,7 @@ Call this tool to get shape names and usage syntax for a specific library.`,
 
     const response = result.toUIMessageStreamResponse({
         sendReasoning: true,
-        // The same text goes back to the model when its tool call was
-        // invalid, so it can fix it: keep that one as it is
-        onError: (error) =>
-            isToolCallError(error)
-                ? (error as Error).message
-                : JSON.stringify(classifyLLMError(error)),
+        onError: streamErrorText,
         messageMetadata: ({ part }) => {
             if (part.type === "finish") {
                 const usage = (part as any).totalUsage