asepharyana
50371bd2d1
Root cause: 9router combo 'multimodal' routes to cloudflare-ai/@cf/google/
gemma-4-26b-a4b-it which streams ALL output in delta.reasoning_content
(content:"") and finishes with 'length' at max_tokens. llmClient only read
delta.content, so llmVision returned empty → every image moderation fell back
to text-only analysis ('Meskipun analisis gambar gagal' in every ai_analysis).
Fix: extractChunkText() prefers delta.content then falls back to
delta.reasoning_content (also handles message/text/response fields), with
unit tests for the exact 9router chunk shape. Verified live against a real
DB image: oc/mimo-v2.5-free (new first model in the multimodal combo) returns
a proper description in delta.content.
71 lines
2.9 KiB
TypeScript
71 lines
2.9 KiB
TypeScript
// ═══════════════════════════════════════════════════════════════════════════
|
|
// llmClient chunk extraction — reasoning_content fallback (pure, no network)
|
|
// ═══════════════════════════════════════════════════════════════════════════
|
|
// Regression: 9router "multimodal" combo routed to cloudflare gemma-4-26b
|
|
// which streams ALL output in delta.reasoning_content with content:"" — the
|
|
// old extractor returned empty text → llmVision reported "Vision API null
|
|
// response" → every image moderation batch fell back to text-only analysis
|
|
// (LLM kept writing "Meskipun analisis gambar gagal").
|
|
import { describe, expect, it } from "vitest";
|
|
import { extractChunkText } from "../src/modules/ai-moderation/llmClient.js";
|
|
|
|
describe("extractChunkText — streaming chunk text extraction", () => {
|
|
it("reads delta.content (standard OpenAI streaming)", () => {
|
|
expect(
|
|
extractChunkText({
|
|
choices: [{ delta: { content: "halo" }, finish_reason: null }],
|
|
}),
|
|
).toBe("halo");
|
|
});
|
|
|
|
it("falls back to delta.reasoning_content when content is empty — reasoning-only models (cloudflare gemma)", () => {
|
|
// Exact shape seen from 9router → cloudflare-ai/@cf/google/gemma-4-26b:
|
|
// {"choices":[{"delta":{"content":"","reasoning_content":"Task","role":"assistant"},"finish_reason":null,...}]}
|
|
expect(
|
|
extractChunkText({
|
|
choices: [
|
|
{
|
|
delta: { content: "", reasoning_content: "Task" },
|
|
finish_reason: null,
|
|
},
|
|
],
|
|
}),
|
|
).toBe("Task");
|
|
});
|
|
|
|
it("prefers content over reasoning when both present (deepseek-style final answer)", () => {
|
|
expect(
|
|
extractChunkText({
|
|
choices: [
|
|
{
|
|
delta: { content: "jawaban akhir", reasoning_content: "pikiran" },
|
|
finish_reason: null,
|
|
},
|
|
],
|
|
}),
|
|
).toBe("jawaban akhir");
|
|
});
|
|
|
|
it("handles Anthropic-style message.content", () => {
|
|
expect(extractChunkText({ message: { content: "via message" } })).toBe(
|
|
"via message",
|
|
);
|
|
});
|
|
|
|
it("handles top-level content / response fields (local LLM proxies)", () => {
|
|
expect(extractChunkText({ content: "top-level" })).toBe("top-level");
|
|
expect(extractChunkText({ response: "via response" })).toBe("via response");
|
|
});
|
|
|
|
it("returns empty string for null/undefined/empty chunks", () => {
|
|
expect(extractChunkText(null)).toBe("");
|
|
expect(extractChunkText(undefined)).toBe("");
|
|
expect(extractChunkText({})).toBe("");
|
|
expect(
|
|
extractChunkText({
|
|
choices: [{ delta: { content: "", reasoning_content: null } }],
|
|
}),
|
|
).toBe("");
|
|
});
|
|
});
|