feat: log llm runtime responses
This commit is contained in:
@@ -10,6 +10,8 @@ describe("generateValidatedJson", () => {
|
||||
afterEach(() => {
|
||||
process.env.LLM_PROVIDER = originalProvider;
|
||||
process.env.DEEPSEEK_API_KEY = originalDeepSeekKey;
|
||||
delete process.env.LLM_LOG_RAW_LIMIT;
|
||||
delete process.env.DEEPSEEK_MODEL;
|
||||
client.setGenerateJsonForValidation(client.generateJson);
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
@@ -103,6 +105,88 @@ describe("generateValidatedJson", () => {
|
||||
);
|
||||
expect(warnSpy).toHaveBeenCalledWith(expect.stringContaining("value"));
|
||||
});
|
||||
|
||||
it("logs provider, model, task, raw response snippet, and validation success", async () => {
|
||||
process.env.LLM_PROVIDER = "deepseek";
|
||||
process.env.DEEPSEEK_API_KEY = "test-key";
|
||||
process.env.DEEPSEEK_MODEL = "deepseek-test";
|
||||
process.env.LLM_LOG_RAW_LIMIT = "80";
|
||||
const infoSpy = vi.spyOn(console, "info").mockImplementation(() => {});
|
||||
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
||||
client.setGenerateJsonForValidation(async () => ({
|
||||
value: "from-llm",
|
||||
longField: "x".repeat(200),
|
||||
}));
|
||||
|
||||
const result = await client.generateValidatedJson({
|
||||
schema: z.object({ value: z.string(), longField: z.string() }),
|
||||
task: "article_optimizer",
|
||||
prompt: "Return JSON.",
|
||||
});
|
||||
|
||||
expect(result?.value).toBe("from-llm");
|
||||
expect(infoSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining(
|
||||
"[llm:start] provider=deepseek model=deepseek-test task=article_optimizer",
|
||||
),
|
||||
);
|
||||
expect(infoSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining("[llm:response] task=article_optimizer"),
|
||||
);
|
||||
expect(infoSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining('"value":"from-llm"'),
|
||||
);
|
||||
expect(infoSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining("[llm:validated] task=article_optimizer ok=true"),
|
||||
);
|
||||
expect(warnSpy).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("logs validation failure without leaking provider secrets", async () => {
|
||||
process.env.LLM_PROVIDER = "deepseek";
|
||||
process.env.DEEPSEEK_API_KEY = "super-secret-key";
|
||||
process.env.DEEPSEEK_MODEL = "deepseek-test";
|
||||
const infoSpy = vi.spyOn(console, "info").mockImplementation(() => {});
|
||||
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
||||
client.setGenerateJsonForValidation(async () => ({ value: 42 }));
|
||||
|
||||
const result = await client.generateValidatedJson({
|
||||
schema: z.object({ value: z.string() }),
|
||||
task: "fact_extractor",
|
||||
prompt: "Return JSON.",
|
||||
});
|
||||
|
||||
const allLogs = [...infoSpy.mock.calls, ...warnSpy.mock.calls]
|
||||
.flat()
|
||||
.join("\n");
|
||||
expect(result).toBeNull();
|
||||
expect(allLogs).toContain("[llm:validated] task=fact_extractor ok=false");
|
||||
expect(allLogs).toContain("zod_error=");
|
||||
expect(allLogs).not.toContain("super-secret-key");
|
||||
});
|
||||
|
||||
it("logs provider call failure for validated JSON calls", async () => {
|
||||
process.env.LLM_PROVIDER = "deepseek";
|
||||
process.env.DEEPSEEK_API_KEY = "test-key";
|
||||
const warnSpy = vi.spyOn(console, "warn").mockImplementation(() => {});
|
||||
client.setGenerateJsonForValidation(async () => {
|
||||
throw new Error("provider unavailable");
|
||||
});
|
||||
|
||||
const result = await client.generateValidatedJson({
|
||||
schema: z.object({ value: z.string() }),
|
||||
task: "quality_inspector",
|
||||
prompt: "Return JSON.",
|
||||
});
|
||||
|
||||
expect(result).toBeNull();
|
||||
expect(warnSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining("[llm:error] task=quality_inspector"),
|
||||
);
|
||||
expect(warnSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining("provider unavailable"),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe("generateJson logging", () => {
|
||||
|
||||
+32
-3
@@ -1,12 +1,19 @@
|
||||
import OpenAI from "openai";
|
||||
import type { z } from "zod";
|
||||
|
||||
export type LlmTaskName =
|
||||
| "unknown"
|
||||
| "fact_extractor"
|
||||
| "article_optimizer"
|
||||
| "quality_inspector"
|
||||
| "targeted_rewriter";
|
||||
|
||||
export interface GenerateInput {
|
||||
system?: string;
|
||||
prompt: string;
|
||||
model?: string;
|
||||
temperature?: number;
|
||||
task?: string;
|
||||
task?: LlmTaskName;
|
||||
}
|
||||
|
||||
export interface GenerateValidatedJsonInput<T> extends GenerateInput {
|
||||
@@ -77,7 +84,16 @@ function getTask(input: GenerateInput) {
|
||||
return input.task?.trim() || "unknown";
|
||||
}
|
||||
|
||||
function truncateRaw(value: string, maxLength = 4000) {
|
||||
function getRawLogLimit() {
|
||||
const parsed = Number(process.env.LLM_LOG_RAW_LIMIT ?? "4000");
|
||||
return Number.isFinite(parsed) && parsed >= 0 ? parsed : 4000;
|
||||
}
|
||||
|
||||
function stringifyForLog(value: unknown) {
|
||||
return typeof value === "string" ? value : JSON.stringify(value);
|
||||
}
|
||||
|
||||
function truncateRaw(value: string, maxLength = getRawLogLimit()) {
|
||||
return value.length > maxLength
|
||||
? `${value.slice(0, maxLength)}...[truncated ${value.length - maxLength} chars]`
|
||||
: value;
|
||||
@@ -195,8 +211,17 @@ export async function generateValidatedJson<T>({
|
||||
return null;
|
||||
}
|
||||
|
||||
const status = getLlmProviderStatus();
|
||||
const startedAt = Date.now();
|
||||
console.info(
|
||||
`[llm:start] provider=${status.provider} model=${input.model ?? status.model} task=${task}`,
|
||||
);
|
||||
|
||||
try {
|
||||
const generated = await generateJsonForValidation<unknown>(input);
|
||||
console.info(
|
||||
`[llm:response] task=${task} duration_ms=${Date.now() - startedAt} raw=${truncateRaw(stringifyForLog(generated))}`,
|
||||
);
|
||||
const parsed = schema.safeParse(generated);
|
||||
if (parsed.success) {
|
||||
console.info(`[llm:validated] task=${task} ok=true`);
|
||||
@@ -206,8 +231,12 @@ export async function generateValidatedJson<T>({
|
||||
`[llm:validated] task=${task} ok=false zod_error=${quoteLogValue(summarizeZodError(parsed.error))}`,
|
||||
);
|
||||
return null;
|
||||
} catch {
|
||||
} catch (error) {
|
||||
console.info(`[llm:validated] task=${task} ok=false reason=provider_error`);
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
console.warn(
|
||||
`[llm:error] task=${task} duration_ms=${Date.now() - startedAt} message=${quoteLogValue(message)}`,
|
||||
);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user