fix: sanitize assistant session text (#1456) (thanks @zerone0x)

src/agents/tools/sessions-helpers.test.ts

@@ -0,0 +1,34 @@
+import { describe, expect, it } from "vitest";
+
+import { extractAssistantText, sanitizeTextContent } from "./sessions-helpers.js";
+
+describe("sanitizeTextContent", () => {
+  it("strips minimax tool call XML and downgraded markers", () => {
+    const input =
+      'Hello <invoke name="tool">payload</invoke></minimax:tool_call> ' +
+      "[Tool Call: foo (ID: 1)] world";
+    const result = sanitizeTextContent(input).trim();
+    expect(result).toBe("Hello  world");
+    expect(result).not.toContain("invoke");
+    expect(result).not.toContain("Tool Call");
+  });
+
+  it("strips thinking tags", () => {
+    const input = "Before <think>secret</think> after";
+    const result = sanitizeTextContent(input).trim();
+    expect(result).toBe("Before  after");
+  });
+});
+
+describe("extractAssistantText", () => {
+  it("sanitizes blocks without injecting newlines", () => {
+    const message = {
+      role: "assistant",
+      content: [
+        { type: "text", text: "Hi " },
+        { type: "text", text: "<think>secret</think>there" },
+      ],
+    };
+    expect(extractAssistantText(message)).toBe("Hi there");
+  });
+});

src/agents/tools/sessions-helpers.ts

@@ -111,9 +111,8 @@ export function stripToolMessages(messages: unknown[]): unknown[] {
  * This ensures user-facing text doesn't leak internal tool representations.
  */
 export function sanitizeTextContent(text: string): string {
-  return stripThinkingTagsFromText(
-    stripDowngradedToolCallText(stripMinimaxToolCallXml(text)),
-  ).trim();
+  if (!text) return text;
+  return stripThinkingTagsFromText(stripDowngradedToolCallText(stripMinimaxToolCallXml(text)));
 }
 
 export function extractAssistantText(message: unknown): string | undefined {
@@ -128,11 +127,11 @@ export function extractAssistantText(message: unknown): string | undefined {
     const text = (block as { text?: unknown }).text;
     if (typeof text === "string") {
       const sanitized = sanitizeTextContent(text);
-      if (sanitized) {
+      if (sanitized.trim()) {
         chunks.push(sanitized);
       }
     }
   }
-  const joined = chunks.join("\n").trim();
+  const joined = chunks.join("").trim();
   return joined ? sanitizeUserFacingText(joined) : undefined;
 }