feat: add OpenRouter provider to golden harness, close Phase 0 gate

- provider-agnostic llm-client (grok + openrouter) with page-slug context
- live golden run scored and passing via x-ai/grok-4.6
- ADR 0010; spike docs flipped to done
This commit is contained in:
SinachPat
2026-08-15 17:58:09 +01:00
parent f42549c451
commit 0d6afab425
9 changed files with 200 additions and 26 deletions
+98
View File
@@ -0,0 +1,98 @@
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import { resolveProvider, callLlm } from '../src/llm-client.ts';
let fetchMock: ReturnType<typeof vi.fn>;
beforeEach(() => {
fetchMock = vi.fn();
vi.stubGlobal('fetch', fetchMock);
});
afterEach(() => {
vi.unstubAllGlobals();
});
describe('resolveProvider', () => {
it('maps grok to the x.ai endpoint and grok-3 model', () => {
expect(resolveProvider('grok')).toEqual({ baseUrl: 'https://api.x.ai/v1', model: 'grok-3' });
});
it('maps openrouter to the openrouter endpoint and the grok-4.6 model', () => {
expect(resolveProvider('openrouter')).toEqual({
baseUrl: 'https://openrouter.ai/api/v1',
model: 'x-ai/grok-4.6',
});
});
it('honors an explicit model override', () => {
expect(resolveProvider('openrouter', 'openai/gpt-4o')).toEqual({
baseUrl: 'https://openrouter.ai/api/v1',
model: 'openai/gpt-4o',
});
});
});
describe('callLlm', () => {
it('posts an OpenAI-shaped tool-call request to the grok endpoint', async () => {
fetchMock.mockResolvedValue({ ok: true, json: async () => ({ choices: [] }) });
await callLlm({
provider: 'grok',
apiKey: 'test-key',
prompt: 'Change the heading',
siteId: 'gutenberg-business',
builder: 'gutenberg',
});
const [url, init] = fetchMock.mock.calls[0] as [string, { headers: Record<string, string>; body: string }];
expect(url).toBe('https://api.x.ai/v1/chat/completions');
expect(init.headers.Authorization).toBe('Bearer test-key');
const body = JSON.parse(init.body) as { model: string; tool_choice: string; tools: Array<{ function: { name: string } }> };
expect(body.model).toBe('grok-3');
expect(body.tool_choice).toBe('required');
expect(body.tools[0]?.function.name).toBe('edit_heading');
});
it('adds OpenRouter identification headers and uses the openrouter endpoint', async () => {
fetchMock.mockResolvedValue({ ok: true, json: async () => ({ choices: [] }) });
await callLlm({
provider: 'openrouter',
apiKey: 'test-key',
prompt: 'Change the heading',
siteId: 'gutenberg-business',
builder: 'gutenberg',
});
const [url, init] = fetchMock.mock.calls[0] as [string, { headers: Record<string, string>; body: string }];
expect(url).toBe('https://openrouter.ai/api/v1/chat/completions');
expect(init.headers['HTTP-Referer']).toBeDefined();
expect(init.headers['X-Title']).toBeDefined();
expect(JSON.parse(init.body).model).toBe('x-ai/grok-4.6');
});
it('includes page slugs in the user message when provided', async () => {
fetchMock.mockResolvedValue({ ok: true, json: async () => ({ choices: [] }) });
await callLlm({
provider: 'grok',
apiKey: 'test-key',
prompt: 'Change the heading',
siteId: 'gutenberg-business',
builder: 'gutenberg',
pages: ['homepage', 'about', 'contact'],
});
const [, init] = fetchMock.mock.calls[0] as [string, { body: string }];
const body = JSON.parse(init.body) as { messages: Array<{ content: string }> };
expect(body.messages[1]?.content).toContain('pages=homepage,about,contact');
});
it('throws when the provider returns a non-ok response', async () => {
fetchMock.mockResolvedValue({ ok: false, status: 401 });
await expect(
callLlm({ provider: 'grok', apiKey: 'bad', prompt: 'x', siteId: 's', builder: 'b' }),
).rejects.toThrow('LLM HTTP 401');
});
});
+2 -2
View File
@@ -2,8 +2,8 @@
"fixturePassed": 20,
"fixtureTotal": 20,
"grokLive": {
"skipped": true,
"reason": "XAI_API_KEY not set"
"id": "gb-01",
"passed": true
},
"scores": [
{
@@ -1,21 +1,47 @@
import type { GrokResponse } from './types.ts';
const url = 'https://api.x.ai/v1/chat/completions';
export type LlmProvider = 'grok' | 'openrouter';
export async function callGrok(input: {
export type LlmConfig = {
baseUrl: string;
model: string;
};
const PROVIDERS: Record<LlmProvider, LlmConfig> = {
grok: { baseUrl: 'https://api.x.ai/v1', model: 'grok-3' },
openrouter: { baseUrl: 'https://openrouter.ai/api/v1', model: 'x-ai/grok-4.6' },
};
export function resolveProvider(provider: LlmProvider, model?: string): LlmConfig {
const config = PROVIDERS[provider];
return { baseUrl: config.baseUrl, model: model ?? config.model };
}
export async function callLlm(input: {
provider: LlmProvider;
apiKey: string;
model?: string;
prompt: string;
siteId: string;
builder: string;
pages?: string[];
}): Promise<GrokResponse> {
const response = await fetch(url, {
const { baseUrl, model } = resolveProvider(input.provider, input.model);
const headers: Record<string, string> = {
Authorization: `Bearer ${input.apiKey}`,
'Content-Type': 'application/json',
};
if (input.provider === 'openrouter') {
headers['HTTP-Referer'] = 'https://wursor.dev';
headers['X-Title'] = 'Wursor golden harness';
}
const response = await fetch(`${baseUrl}/chat/completions`, {
method: 'POST',
headers: {
Authorization: `Bearer ${input.apiKey}`,
'Content-Type': 'application/json',
},
headers,
body: JSON.stringify({
model: 'grok-3',
model,
messages: [
{
role: 'system',
@@ -24,7 +50,7 @@ export async function callGrok(input: {
},
{
role: 'user',
content: `site=${input.siteId} builder=${input.builder}\n${input.prompt}`,
content: `site=${input.siteId} builder=${input.builder}${input.pages ? ` pages=${input.pages.join(',')}` : ''}\n${input.prompt}`,
},
],
tools: [
@@ -71,7 +97,7 @@ export async function callGrok(input: {
});
if (!response.ok) {
throw new Error(`Grok HTTP ${response.status}`);
throw new Error(`LLM HTTP ${response.status}`);
}
return (await response.json()) as GrokResponse;
}
+14 -4
View File
@@ -3,15 +3,19 @@ import { dirname, join } from 'node:path';
import { fileURLToPath } from 'node:url';
import { detectBuilder } from './builder-detect.ts';
import { asGrokResponse, expectedCalls } from './expected-calls.ts';
import { callGrok } from './grok-client.ts';
import { callLlm, type LlmProvider } from './llm-client.ts';
import { loadPrompts } from './load-prompts.ts';
import { loadSite } from './load-site.ts';
import { scoreGrokResponse } from './score.ts';
const goldenRoot = join(dirname(fileURLToPath(import.meta.url)), '..');
function provider(): LlmProvider {
return process.env.LLM_PROVIDER === 'openrouter' ? 'openrouter' : 'grok';
}
function key(): string | undefined {
const value = process.env.XAI_API_KEY;
const value = provider() === 'openrouter' ? process.env.OPENROUTER_API_KEY : process.env.XAI_API_KEY;
return value !== undefined && value !== '' ? value : undefined;
}
@@ -39,11 +43,14 @@ if (apiKey !== undefined) {
}
const site = loadSite(prompt.site);
try {
const grok = await callGrok({
const grok = await callLlm({
provider: provider(),
apiKey,
model: provider() === 'openrouter' ? process.env.OPENROUTER_MODEL : undefined,
prompt: prompt.prompt,
siteId: site.id,
builder: detectBuilder(site),
pages: site.posts.map((post) => post.slug),
});
grokLive = {
id: prompt.id,
@@ -57,7 +64,10 @@ if (apiKey !== undefined) {
const report = {
fixturePassed: fixtureScores.filter((row) => row.passed).length,
fixtureTotal: fixtureScores.length,
grokLive: grokLive ?? { skipped: true, reason: 'XAI_API_KEY not set' },
grokLive: grokLive ?? {
skipped: true,
reason: provider() === 'openrouter' ? 'OPENROUTER_API_KEY not set' : 'XAI_API_KEY not set',
},
scores: fixtureScores,
};