refactor(shared): dedupe chat content text extraction

This commit is contained in:
Peter Steinberger
2026-02-15 17:21:36 +00:00
parent ac3db098ab
commit b74c3d80cc
4 changed files with 71 additions and 61 deletions

View File

@@ -0,0 +1,26 @@
import { describe, expect, it } from "vitest";
import { extractTextFromChatContent } from "./chat-content.js";
describe("extractTextFromChatContent", () => {
it("normalizes string content", () => {
expect(extractTextFromChatContent(" hello\nworld ")).toBe("hello world");
});
it("extracts text blocks from array content", () => {
expect(
extractTextFromChatContent([
{ type: "text", text: " hello " },
{ type: "image_url", image_url: "https://example.com" },
{ type: "text", text: "world" },
]),
).toBe("hello world");
});
it("applies sanitizer when provided", () => {
expect(
extractTextFromChatContent("Here [Tool Call: foo (ID: 1)] ok", {
sanitizeText: (text) => text.replace(/\[Tool Call:[^\]]+\]\s*/g, ""),
}),
).toBe("Here ok");
});
});

View File

@@ -0,0 +1,37 @@
export function extractTextFromChatContent(
content: unknown,
opts?: { sanitizeText?: (text: string) => string },
): string | null {
const normalize = (text: string) => text.replace(/\s+/g, " ").trim();
if (typeof content === "string") {
const value = opts?.sanitizeText ? opts.sanitizeText(content) : content;
const normalized = normalize(value);
return normalized ? normalized : null;
}
if (!Array.isArray(content)) {
return null;
}
const chunks: string[] = [];
for (const block of content) {
if (!block || typeof block !== "object") {
continue;
}
if ((block as { type?: unknown }).type !== "text") {
continue;
}
const text = (block as { text?: unknown }).text;
if (typeof text !== "string") {
continue;
}
const value = opts?.sanitizeText ? opts.sanitizeText(text) : text;
if (value.trim()) {
chunks.push(value);
}
}
const joined = normalize(chunks.join(" "));
return joined ? joined : null;
}