feat: improve outbound message chunking with code-block-aware splitting

- Increase max message length from 4000 to 8000 chars - Add splitAtBoundary: paragraph > newline > space priority, never split inside fenced code blocks (move split to before opening fence) - Add sendLongText: sends multi-chunk long messages sequentially - Update PatchableTextStream.flush to use splitAtBoundary - Add unit tests (6) for splitting edge cases
2026-07-08 16:57:53 +08:00
parent 4736610cf3
commit bef10149a9
4 changed files with 196 additions and 10 deletions
@@ -9,6 +9,7 @@ import * as lark from "@larksuiteoapi/node-sdk";
 import { readFile, writeFile, mkdir } from "node:fs/promises";
 import { dirname } from "node:path";
 import type { FastifyBaseLogger } from "fastify";
+import { DEFAULT_MAX_MESSAGE_LENGTH, splitAtBoundary } from "./textStream.js";

 export interface FeishuConfig {
  readonly appId: string;
@@ -157,6 +158,18 @@ export async function sendTextMessage(rt: FeishuRuntime, chatId: string, text: s
  }
 }

+/** Send long text as multiple Feishu messages. Returns the last successful message_id. */
+export async function sendLongText(rt: FeishuRuntime, chatId: string, text: string): Promise<string | null> {
+  let lastMessageId: string | null = null;
+  for (const chunk of splitAtBoundary(text, DEFAULT_MAX_MESSAGE_LENGTH)) {
+    const messageId = await sendTextMessage(rt, chatId, chunk);
+    if (messageId !== null) {
+      lastMessageId = messageId;
+    }
+  }
+  return lastMessageId;
+}
+
 /** Send a plain text message (fire-and-forget). */
 export async function sendText(rt: FeishuRuntime, chatId: string, text: string): Promise<void> {
  await sendTextMessage(rt, chatId, text);
@@ -9,7 +9,107 @@ export interface PatchableTextStreamOptions {
 }

 const DEFAULT_PATCH_INTERVAL_MS = 400;
-const DEFAULT_MAX_MESSAGE_LENGTH = 4000;
+export const DEFAULT_MAX_MESSAGE_LENGTH = 8000;
+
+interface CodeBlockRange {
+  readonly start: number;
+  readonly end: number;
+}
+
+export function splitAtBoundary(text: string, maxLength: number): string[] {
+  if (!Number.isInteger(maxLength) || maxLength <= 0) {
+    throw new RangeError("maxLength must be a positive integer");
+  }
+  if (text.length <= maxLength) return [text];
+
+  const chunks: string[] = [];
+  let remaining = text;
+  while (remaining.length > maxLength) {
+    const splitPoint = chooseSplitPoint(remaining, maxLength);
+    if (splitPoint <= 0) {
+      const codeBlockEnd = codeBlockAtStartEnd(remaining);
+      const forcedSplitPoint = codeBlockEnd ?? maxLength;
+      chunks.push(remaining.slice(0, forcedSplitPoint));
+      remaining = remaining.slice(forcedSplitPoint);
+      continue;
+    }
+
+    chunks.push(remaining.slice(0, splitPoint));
+    remaining = remaining.slice(splitPoint);
+  }
+  if (remaining.length > 0) {
+    chunks.push(remaining);
+  }
+  return chunks;
+}
+
+function chooseSplitPoint(text: string, maxLength: number): number {
+  const codeBlocks = findFencedCodeBlocks(text);
+  const splitCodeBlock = codeBlocks.find((range) => maxLength > range.start && maxLength < range.end);
+  if (splitCodeBlock !== undefined) {
+    return splitCodeBlock.start;
+  }
+
+  return (
+    lastBoundary(text, maxLength, /\r?\n\r?\n/g, codeBlocks) ??
+    lastBoundary(text, maxLength, /\r?\n/g, codeBlocks) ??
+    lastBoundary(text, maxLength, / /g, codeBlocks) ??
+    maxLength
+  );
+}
+
+function lastBoundary(text: string, maxLength: number, pattern: RegExp, codeBlocks: ReadonlyArray<CodeBlockRange>): number | undefined {
+  let boundary: number | undefined;
+  let match: RegExpExecArray | null;
+  pattern.lastIndex = 0;
+  while ((match = pattern.exec(text)) !== null) {
+    const splitPoint = match.index + match[0].length;
+    if (splitPoint > maxLength) break;
+    if (splitPoint > 0 && !isInsideCodeBlock(splitPoint, codeBlocks)) {
+      boundary = splitPoint;
+    }
+  }
+  return boundary;
+}
+
+function isInsideCodeBlock(splitPoint: number, codeBlocks: ReadonlyArray<CodeBlockRange>): boolean {
+  return codeBlocks.some((range) => splitPoint > range.start && splitPoint < range.end);
+}
+
+function codeBlockAtStartEnd(text: string): number | undefined {
+  const firstCodeBlock = findFencedCodeBlocks(text)[0];
+  return firstCodeBlock?.start === 0 ? firstCodeBlock.end : undefined;
+}
+
+function findFencedCodeBlocks(text: string): CodeBlockRange[] {
+  const ranges: CodeBlockRange[] = [];
+  let openStart: number | null = null;
+  let lineStart = 0;
+
+  while (lineStart < text.length) {
+    const newlineIndex = text.indexOf("\n", lineStart);
+    const lineEnd = newlineIndex === -1 ? text.length : newlineIndex;
+    const nextLineStart = newlineIndex === -1 ? text.length : newlineIndex + 1;
+    const line = text.slice(lineStart, lineEnd);
+
+    if (/^ {0,3}```/.test(line)) {
+      if (openStart === null) {
+        openStart = lineStart;
+      } else {
+        ranges.push({ start: openStart, end: nextLineStart });
+        openStart = null;
+      }
+    }
+
+    lineStart = nextLineStart;
+  }
+
+  if (openStart !== null) {
+    ranges.push({ start: openStart, end: text.length });
+  }
+
+  return ranges;
+}

 /**
 * Serializes text-card creation/patching for streaming output.
@@ -45,11 +145,12 @@ export class PatchableTextStream {
  async finish(fallbackText: string): Promise<void> {
    await this.flushChain;
    if (this.currentMessageId !== null && this.text.length > 0) {
-      await this.sink.patch(this.currentMessageId, this.text);
+      await this.flushTextToSink();
      return;
    }
    if (this.currentMessageId === null && fallbackText.length > 0) {
-      this.currentMessageId = await this.sink.create(fallbackText);
+      this.text = fallbackText;
+      await this.flushTextToSink();
    }
  }

@@ -64,7 +165,7 @@ export class PatchableTextStream {

  private async flush(): Promise<void> {
    if (this.currentMessageId === null) {
-      this.currentMessageId = await this.sink.create(this.text);
+      await this.flushTextToSink();
      this.lastPatchAt = Date.now();
      return;
    }
@@ -73,12 +174,26 @@ export class PatchableTextStream {
    if (now - this.lastPatchAt < this.patchIntervalMs) return;
    this.lastPatchAt = now;

-    if (this.text.length > this.maxMessageLength) {
-      await this.sink.patch(this.currentMessageId, this.text.slice(0, this.maxMessageLength));
-      this.text = this.text.slice(this.maxMessageLength);
-      this.currentMessageId = await this.sink.create(this.text);
+    await this.flushTextToSink();
+  }
+
+  private async flushTextToSink(): Promise<void> {
+    const textToFlush = this.text;
+    const chunks = splitAtBoundary(textToFlush, this.maxMessageLength);
+    const firstChunk = chunks[0];
+    if (firstChunk === undefined) return;
+
+    if (this.currentMessageId === null) {
+      for (const chunk of chunks) {
+        this.currentMessageId = await this.sink.create(chunk);
+      }
    } else {
-      await this.sink.patch(this.currentMessageId, this.text);
+      await this.sink.patch(this.currentMessageId, firstChunk);
+      for (const chunk of chunks.slice(1)) {
+        this.currentMessageId = await this.sink.create(chunk);
+      }
    }
+    const appendedDuringFlush = this.text.startsWith(textToFlush) ? this.text.slice(textToFlush.length) : "";
+    this.text = `${chunks.at(-1) ?? ""}${appendedDuringFlush}`;
  }
 }
@@ -2,7 +2,7 @@ import { describe, expect, it, vi } from "vitest";
 import { mkdtemp, rm, writeFile } from "node:fs/promises";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
-import { sendFile, sendTextMessage, type FeishuRuntime } from "../../src/feishu/client.js";
+import { sendFile, sendLongText, sendTextMessage, type FeishuRuntime } from "../../src/feishu/client.js";

 describe("Feishu client helpers", () => {
  it("accepts top-level file_key from the Lark SDK file upload response", async () => {
@@ -32,6 +32,21 @@ describe("Feishu client helpers", () => {

    await expect(sendTextMessage(rt, "chat-1", "hello")).resolves.toBe("message-1");
  });
+
+  it("sends long text in chunks and returns the last successful message id", async () => {
+    let messageNumber = 0;
+    const messageCreate = vi.fn(async () => ({ data: { message_id: `message-${++messageNumber}` } }));
+    const rt = mockRuntime({ fileCreate: vi.fn(), messageCreate });
+
+    await expect(sendLongText(rt, "chat-1", "x".repeat(16_005))).resolves.toBe("message-3");
+
+    expect(messageCreate).toHaveBeenCalledTimes(3);
+    const sentTexts = messageCreate.mock.calls.map(([payload]) => {
+      const content = (payload as { data: { content: string } }).data.content;
+      return (JSON.parse(content) as { text: string }).text;
+    });
+    expect(sentTexts.map((text) => text.length)).toEqual([8000, 8000, 5]);
+  });
 });

 function mockRuntime(options: {
@@ -0,0 +1,43 @@
+import { describe, expect, it } from "vitest";
+import { splitAtBoundary } from "../../src/feishu/textStream.js";
+
+describe("splitAtBoundary", () => {
+  it("keeps short text in a single chunk", () => {
+    expect(splitAtBoundary("short text", 20)).toEqual(["short text"]);
+  });
+
+  it("keeps text at exactly maxLength in a single chunk", () => {
+    const text = "x".repeat(20);
+
+    expect(splitAtBoundary(text, 20)).toEqual([text]);
+  });
+
+  it("splits text exceeding maxLength into chunks at or below maxLength", () => {
+    const chunks = splitAtBoundary("x".repeat(45), 20);
+
+    expect(chunks).toHaveLength(3);
+    expect(chunks.every((chunk) => chunk.length <= 20)).toBe(true);
+    expect(chunks.join("")).toBe("x".repeat(45));
+  });
+
+  it("moves a split before a fenced code block when the boundary lands inside it", () => {
+    const prefix = "Before code starts\n";
+    const codeBlock = "```ts\nx\n```\n";
+    const text = `${prefix}${codeBlock}After`;
+    const chunks = splitAtBoundary(text, prefix.length + 4);
+
+    expect(chunks).toEqual([prefix, `${codeBlock}After`]);
+  });
+
+  it("prefers paragraph boundaries over newline boundaries", () => {
+    const text = "para one\n\nline two\nline three";
+
+    expect(splitAtBoundary(text, 22)).toEqual(["para one\n\n", "line two\nline three"]);
+  });
+
+  it("prefers newline boundaries over space boundaries", () => {
+    const text = "alpha beta\ngamma delta epsilon";
+
+    expect(splitAtBoundary(text, 24)).toEqual(["alpha beta\n", "gamma delta epsilon"]);
+  });
+});