fix(frontend): exclude hidden, reasoning, and tool payloads from chat export

`formatThreadAsMarkdown` / `formatThreadAsJSON` iterated raw messages without running the UI-level `isHiddenFromUIMessage` filter. Exported transcripts therefore included `hide_from_ui` system reminders, memory injections, provider `reasoning_content`, tool calls, and tool result messages — content that is intentionally hidden in the chat view. Filter the export to the user-visible transcript by default and gate reasoning / tool calls / tool messages / hidden messages behind explicit `ExportOptions` flags so a future debug export can opt back in without forking the formatter. Refs: bytedance/deer-flow#3107 (BUG-006)
2026-05-23 00:16:48 +00:00 · 2026-05-21 15:08:59 +08:00
parent 308d43c9bd
commit 9b77ef160f
2 changed files with 180 additions and 5 deletions
@@ -0,0 +1,134 @@
+import type { Message } from "@langchain/langgraph-sdk";
+import { describe, expect, it } from "vitest";
+
+import {
+  formatThreadAsJSON,
+  formatThreadAsMarkdown,
+} from "@/core/threads/export";
+import type { AgentThread } from "@/core/threads/types";
+
+// Bytedance/deer-flow issue #3107 BUG-006: the chat export path bypasses the
+// UI-level hidden-message filter and emits reasoning content, tool calls, and
+// any other "internal" payload as if it were part of the user transcript.
+
+function makeThread(): AgentThread {
+  return {
+    thread_id: "thread-1",
+    created_at: "2026-05-21T00:00:00Z",
+    updated_at: "2026-05-21T00:00:00Z",
+    metadata: { title: "Demo thread" },
+    status: "idle",
+    values: { messages: [] },
+  } as unknown as AgentThread;
+}
+
+function human(content: string, extra: Partial<Message> = {}): Message {
+  return {
+    id: `h-${content}`,
+    type: "human",
+    content,
+    ...extra,
+  } as Message;
+}
+
+function ai(
+  content: string,
+  extra: Partial<Message> & { tool_calls?: unknown } = {},
+): Message {
+  return {
+    id: `a-${content}`,
+    type: "ai",
+    content,
+    ...extra,
+  } as Message;
+}
+
+function toolMsg(content: string): Message {
+  return {
+    id: `t-${content}`,
+    type: "tool",
+    content,
+    name: "task",
+    tool_call_id: "call-1",
+  } as unknown as Message;
+}
+
+describe("formatThreadAsMarkdown", () => {
+  it("includes plain user and assistant text", () => {
+    const md = formatThreadAsMarkdown(makeThread(), [
+      human("hello"),
+      ai("hi there"),
+    ]);
+    expect(md).toContain("hello");
+    expect(md).toContain("hi there");
+  });
+
+  it("drops messages marked hide_from_ui", () => {
+    const hidden = human("internal system reminder", {
+      additional_kwargs: { hide_from_ui: true },
+    } as Partial<Message>);
+    const md = formatThreadAsMarkdown(makeThread(), [
+      hidden,
+      ai("public answer"),
+    ]);
+    expect(md).not.toContain("internal system reminder");
+    expect(md).toContain("public answer");
+  });
+
+  it("does not emit reasoning_content by default", () => {
+    const message = ai("final answer", {
+      additional_kwargs: {
+        reasoning_content: "secret chain of thought",
+      },
+    } as Partial<Message>);
+    const md = formatThreadAsMarkdown(makeThread(), [message]);
+    expect(md).not.toContain("secret chain of thought");
+    expect(md).not.toContain("Thinking");
+  });
+
+  it("does not emit tool calls by default", () => {
+    const message = ai("ok", {
+      tool_calls: [{ id: "1", name: "task", args: { description: "do work" } }],
+    } as Partial<Message>);
+    const md = formatThreadAsMarkdown(makeThread(), [message]);
+    expect(md).not.toContain("**Tool:**");
+    expect(md).not.toContain("`task`");
+  });
+
+  it("drops tool result messages", () => {
+    const md = formatThreadAsMarkdown(makeThread(), [
+      ai("delegating"),
+      toolMsg("Task Succeeded. Result: confidential"),
+    ]);
+    expect(md).not.toContain("confidential");
+  });
+});
+
+describe("formatThreadAsJSON", () => {
+  it("strips hidden messages, tool messages, reasoning, and tool calls", () => {
+    const messages = [
+      human("hello"),
+      human("secret reminder", {
+        additional_kwargs: { hide_from_ui: true },
+      } as Partial<Message>),
+      ai("answer", {
+        additional_kwargs: {
+          reasoning_content: "secret reasoning",
+        },
+        tool_calls: [{ id: "1", name: "task", args: {} }],
+      } as Partial<Message>),
+      toolMsg("internal trace"),
+    ];
+    const raw = formatThreadAsJSON(makeThread(), messages);
+    const parsed = JSON.parse(raw) as {
+      messages: { type: string; tool_calls?: unknown[] }[];
+    };
+
+    expect(parsed.messages).toHaveLength(2);
+    expect(parsed.messages.every((m) => m.type !== "tool")).toBe(true);
+    expect(raw).not.toContain("secret reminder");
+    expect(raw).not.toContain("secret reasoning");
+    expect(raw).not.toContain("internal trace");
+    expect(raw).not.toContain("tool_calls");
+  });
+});