mirror of
https://github.com/FJurmanovic/sugarr.git
synced 2026-11-11 15:51:09 +00:00
LangfuseTracer was passing our internal camelCase usage fields (promptTokens/completionTokens/totalTokens) straight through as usageDetails. Langfuse only recognizes a flat schema (input/output/...) or OpenAI's native snake_case schema (prompt_tokens/completion_tokens/ total_tokens) for usage/cost calculation - anything else is silently ignored, so every generation was showing zero usage regardless of what LlmClient actually reported. Note: cost still requires a price-list entry for the model name. Langfuse's built-in list only covers hosted providers (OpenAI, Anthropic, Google); self-hosted models (e.g. LLM_MODEL=llama3 via Ollama) need a custom model price added in Project Settings > Models for a $ figure to show up, even with token counts now correct. Verified: full suite (80/80) passing, tsc/eslint clean.
113 lines
4.4 KiB
TypeScript
113 lines
4.4 KiB
TypeScript
import { describe, expect, it, vi } from 'vitest';
|
|
|
|
const {
|
|
forceFlush,
|
|
shutdown,
|
|
sdkStart,
|
|
sdkShutdown,
|
|
generationUpdate,
|
|
generationEnd,
|
|
childStartObservation,
|
|
startObservation,
|
|
propagateAttributes,
|
|
} = vi.hoisted(() => {
|
|
const generationUpdate = vi.fn();
|
|
const generationEnd = vi.fn();
|
|
const generation = { update: generationUpdate, end: generationEnd };
|
|
const childStartObservation = vi.fn().mockReturnValue(generation);
|
|
const rootSpan = { traceId: 'lf-trace-1', startObservation: childStartObservation };
|
|
return {
|
|
forceFlush: vi.fn().mockResolvedValue(undefined),
|
|
shutdown: vi.fn().mockResolvedValue(undefined),
|
|
sdkStart: vi.fn(),
|
|
sdkShutdown: vi.fn().mockResolvedValue(undefined),
|
|
generationUpdate,
|
|
generationEnd,
|
|
childStartObservation,
|
|
startObservation: vi.fn().mockReturnValue(rootSpan),
|
|
propagateAttributes: vi.fn().mockImplementation((_attrs: unknown, fn: () => unknown) => fn()),
|
|
};
|
|
});
|
|
|
|
vi.mock('@langfuse/otel', () => ({
|
|
LangfuseSpanProcessor: vi.fn().mockImplementation(() => ({ forceFlush, shutdown })),
|
|
}));
|
|
|
|
vi.mock('@opentelemetry/sdk-node', () => ({
|
|
NodeSDK: vi.fn().mockImplementation(() => ({ start: sdkStart, shutdown: sdkShutdown })),
|
|
}));
|
|
|
|
vi.mock('@langfuse/tracing', () => ({ startObservation, propagateAttributes }));
|
|
|
|
import { LangfuseTracer } from '../../../src/core/langfuse/LangfuseTracer';
|
|
|
|
describe('LangfuseTracer', () => {
|
|
it('starts the OTEL SDK with a LangfuseSpanProcessor on construction', () => {
|
|
new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
expect(sdkStart).toHaveBeenCalled();
|
|
});
|
|
|
|
it('starts a root observation and exposes its trace id', () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
const handle = tracer.startTrace('my-pipeline', { foo: 'bar' });
|
|
|
|
expect(startObservation).toHaveBeenCalledWith('my-pipeline', { metadata: { foo: 'bar' } });
|
|
expect(handle.id).toBe('lf-trace-1');
|
|
});
|
|
|
|
it('startGeneration creates a child generation observation and end() forwards output/usage', () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
const handle = tracer.startTrace('my-pipeline');
|
|
const gen = handle.startGeneration({ name: 'step-1', model: 'llama3', input: ['hi'] });
|
|
gen.end({
|
|
output: 'done',
|
|
usage: { promptTokens: 10, completionTokens: 5, totalTokens: 15 },
|
|
});
|
|
|
|
expect(childStartObservation).toHaveBeenCalledWith(
|
|
'step-1',
|
|
expect.objectContaining({ model: 'llama3', input: ['hi'] }),
|
|
{ asType: 'generation' }
|
|
);
|
|
expect(generationUpdate).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
output: 'done',
|
|
usageDetails: { prompt_tokens: 10, completion_tokens: 5, total_tokens: 15 },
|
|
})
|
|
);
|
|
expect(generationEnd).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it('omits usageDetails entirely when no usage is reported', () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
const handle = tracer.startTrace('my-pipeline');
|
|
const gen = handle.startGeneration({ name: 'step-1', model: 'llama3', input: ['hi'] });
|
|
gen.end({ output: 'done' });
|
|
|
|
expect(generationUpdate).toHaveBeenCalledWith(expect.objectContaining({ usageDetails: undefined }));
|
|
});
|
|
|
|
it('flush() force-flushes the span processor without shutting down the SDK', async () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
await tracer.flush();
|
|
expect(forceFlush).toHaveBeenCalledTimes(1);
|
|
expect(sdkShutdown).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('shutdown() shuts down the underlying OTEL SDK', async () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
await tracer.shutdown();
|
|
expect(sdkShutdown).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it('runWithSession propagates sessionId/tags to the callback via propagateAttributes and returns its result', async () => {
|
|
const tracer = new LangfuseTracer({ publicKey: 'pk', secretKey: 'sk', baseUrl: 'http://lf' });
|
|
const fn = vi.fn().mockResolvedValue('done');
|
|
|
|
const result = await tracer.runWithSession({ sessionId: 'session-1', tags: ['cron'] }, fn);
|
|
|
|
expect(propagateAttributes).toHaveBeenCalledWith({ sessionId: 'session-1', tags: ['cron'] }, fn);
|
|
expect(result).toBe('done');
|
|
});
|
|
});
|