feat(frontend): split Add detail into a segmented control with voice
The microphone becomes the second segment of the Add detail button, built like the detail chip's trash affordance in the same file — an overflow-hidden rounded wrapper holding two raw <button>s divided by border-s — rather than two shared Buttons, which each hardcode their own rounding and would fight a segmented control. border-s puts the mic at the logical end: visually right in en/nl, visually left in fa, on the same side as the chip's trash in both directions. The two halves share a wrapper and nothing else. Add keeps its exact behaviour. The control never changes size while recording; the timer and level meter live in a bar between the header row and the chip strip, because the header is sm:justify-between and growing the button would shove the row on every start and stop. The meter exists to prove the microphone is actually hearing something — silence and a dead mic look identical otherwise. Voice reaches the editor as one optional `voice` prop, so its absence *is* the unavailable state and the two cannot disagree. Fixes from review of this commit: - mountedRef was set false on unmount and never re-armed, so under StrictMode the hook was permanently "unmounted" in dev and recording silently never started. - onStart guarded only on `phase`, which does not change until getUserMedia resolves; a second click during the permission prompt orphaned the first MediaStream, leaving the mic indicator lit. - Week start is now per locale. "Next Thursday" is week-relative, and hardcoding Saturday put an en/nl clinician's deadline a week out. - A missing `which` on a weekday intent is read as "this" rather than failing — a bare weekday carries no qualifier, and rejecting it discarded a real deadline. - durationMs is client-reported and so is a claim, not enforcement; the cap is now also checked against the vendor's own usage.seconds. - Blob type falls back to the recorder's actual mimeType before webm, so old Safari's mp4/aac clips are not mislabelled. Two review findings were rejected as incorrect, both re-verified against live sources: google/gemini-3.7-flash does exist on OpenRouter (1M context, $0.375/$1.875 per M), and base64 JSON input_audio is the documented primary path for /audio/transcriptions, with multipart as the OpenAI-compatible alternative. The spec's stale "unverified" note is corrected, and the provider now has unit tests covering the request shape, usage parsing, and that a vendor error body never reaches the thrown message. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
197
backend/src/modules/voice/openrouter.provider.spec.ts
Normal file
197
backend/src/modules/voice/openrouter.provider.spec.ts
Normal file
@@ -0,0 +1,197 @@
|
||||
import {
|
||||
OpenRouterAsrProvider,
|
||||
OpenRouterExtractionProvider,
|
||||
} from './openrouter.provider';
|
||||
import { VoiceProviderError } from './voice.providers';
|
||||
|
||||
const CONFIG = {
|
||||
apiKey: 'test-key',
|
||||
baseUrl: 'https://openrouter.test/api/v1',
|
||||
model: 'm',
|
||||
};
|
||||
|
||||
const CATALOG = {
|
||||
treatmentTypes: [{ code: 'prosthesis', label: 'پروتز' }],
|
||||
prosthesisTypes: [{ code: 'pfm_crown', label: 'روکش پیافام' }],
|
||||
labs: [{ id: 'lab-1', name: 'لابراتوار سینا' }],
|
||||
};
|
||||
|
||||
type ChatBody = {
|
||||
temperature: number;
|
||||
provider: { require_parameters: boolean };
|
||||
response_format: { type: string; json_schema: { strict: boolean } };
|
||||
messages: { role: string; content: string }[];
|
||||
};
|
||||
|
||||
function parseBody(spy: jest.Mock): ChatBody {
|
||||
const init = (spy.mock.calls[0] as [string, RequestInit])[1];
|
||||
return JSON.parse(init.body as string) as ChatBody;
|
||||
}
|
||||
|
||||
function mockFetch(response: {
|
||||
ok: boolean;
|
||||
status?: number;
|
||||
body?: unknown;
|
||||
text?: string;
|
||||
}) {
|
||||
const spy = jest.fn().mockResolvedValue({
|
||||
ok: response.ok,
|
||||
status: response.status ?? (response.ok ? 200 : 500),
|
||||
json: () => Promise.resolve(response.body),
|
||||
text: () => Promise.resolve(response.text ?? ''),
|
||||
});
|
||||
global.fetch = spy;
|
||||
return spy;
|
||||
}
|
||||
|
||||
afterEach(() => {
|
||||
jest.restoreAllMocks();
|
||||
});
|
||||
|
||||
describe('OpenRouterAsrProvider', () => {
|
||||
it('posts base64 JSON with the language hint, per the documented STT contract', async () => {
|
||||
const spy = mockFetch({
|
||||
ok: true,
|
||||
body: { text: ' سلام ', usage: { seconds: 12, cost: 0.002 } },
|
||||
});
|
||||
|
||||
const result = await new OpenRouterAsrProvider(CONFIG).transcribe(
|
||||
{ data: 'BASE64', format: 'webm' },
|
||||
'fa',
|
||||
);
|
||||
|
||||
const [url, init] = spy.mock.calls[0] as [string, RequestInit];
|
||||
expect(url).toBe('https://openrouter.test/api/v1/audio/transcriptions');
|
||||
expect(init.headers).toMatchObject({ Authorization: 'Bearer test-key' });
|
||||
expect(JSON.parse(init.body as string)).toEqual({
|
||||
model: 'm',
|
||||
input_audio: { data: 'BASE64', format: 'webm' },
|
||||
language: 'fa',
|
||||
});
|
||||
expect(result.text).toBe('سلام');
|
||||
expect(result.usage).toEqual({ seconds: 12, costUsd: 0.002 });
|
||||
});
|
||||
|
||||
it('reports missing usage as null rather than zero', async () => {
|
||||
mockFetch({ ok: true, body: { text: 'x' } });
|
||||
const result = await new OpenRouterAsrProvider(CONFIG).transcribe(
|
||||
{ data: 'B', format: 'webm' },
|
||||
'en',
|
||||
);
|
||||
expect(result.usage).toEqual({ seconds: null, costUsd: null });
|
||||
});
|
||||
|
||||
it('raises a staged error without leaking the vendor body', async () => {
|
||||
// A 4xx can echo the request back, transcript included.
|
||||
mockFetch({
|
||||
ok: false,
|
||||
status: 400,
|
||||
text: 'transcript: patient name here',
|
||||
});
|
||||
const provider = new OpenRouterAsrProvider(CONFIG);
|
||||
|
||||
await expect(
|
||||
provider.transcribe({ data: 'B', format: 'webm' }, 'fa'),
|
||||
).rejects.toMatchObject({
|
||||
name: 'VoiceProviderError',
|
||||
stage: 'asr',
|
||||
status: 400,
|
||||
});
|
||||
await expect(
|
||||
provider.transcribe({ data: 'B', format: 'webm' }, 'fa'),
|
||||
).rejects.not.toThrow(/patient name/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('OpenRouterExtractionProvider', () => {
|
||||
const wireContent = JSON.stringify({
|
||||
treatmentType: 'prosthesis',
|
||||
teeth: [
|
||||
{ spoken: 'یک چهار', fdi: '14', arch: null, side: null, position: null },
|
||||
],
|
||||
connectedSpans: [],
|
||||
comment: null,
|
||||
prosthesisDefaultType: 'pfm_crown',
|
||||
prosthesisOverrides: [],
|
||||
labId: 'lab-1',
|
||||
labMatchExact: true,
|
||||
due: {
|
||||
kind: 'none',
|
||||
weekday: null,
|
||||
which: null,
|
||||
unit: null,
|
||||
amount: null,
|
||||
jy: null,
|
||||
jm: null,
|
||||
jd: null,
|
||||
y: null,
|
||||
m: null,
|
||||
d: null,
|
||||
},
|
||||
});
|
||||
|
||||
it('constrains output with a strict JSON schema and a schema-honouring provider', async () => {
|
||||
const spy = mockFetch({
|
||||
ok: true,
|
||||
body: {
|
||||
choices: [{ message: { content: wireContent } }],
|
||||
usage: { cost: 0.0008 },
|
||||
},
|
||||
});
|
||||
|
||||
const result = await new OpenRouterExtractionProvider(CONFIG).extract(
|
||||
'روی دندان ۱۴ روکش',
|
||||
CATALOG,
|
||||
'fa',
|
||||
);
|
||||
|
||||
const body = parseBody(spy);
|
||||
expect(body.response_format.type).toBe('json_schema');
|
||||
expect(body.response_format.json_schema.strict).toBe(true);
|
||||
// Without require_parameters OpenRouter may route to a provider that treats the
|
||||
// schema as a hint and returns prose, failing parsing intermittently.
|
||||
expect(body.provider).toEqual({ require_parameters: true });
|
||||
expect(body.temperature).toBe(0);
|
||||
|
||||
expect(result.intent.treatmentType).toBe('prosthesis');
|
||||
expect(result.intent.teeth[0]).toEqual({
|
||||
kind: 'explicit',
|
||||
fdi: '14',
|
||||
spoken: 'یک چهار',
|
||||
});
|
||||
expect(result.intent.due).toBeNull();
|
||||
expect(result.costUsd).toBe(0.0008);
|
||||
});
|
||||
|
||||
it('sends the catalog codes and lab ids the model is allowed to choose from', async () => {
|
||||
const spy = mockFetch({
|
||||
ok: true,
|
||||
body: { choices: [{ message: { content: wireContent } }] },
|
||||
});
|
||||
await new OpenRouterExtractionProvider(CONFIG).extract('x', CATALOG, 'fa');
|
||||
|
||||
const body = parseBody(spy);
|
||||
const system = body.messages[0].content;
|
||||
expect(system).toContain('prosthesis');
|
||||
expect(system).toContain('pfm_crown');
|
||||
expect(system).toContain('lab-1');
|
||||
expect(body.messages[1]).toEqual({ role: 'user', content: 'x' });
|
||||
});
|
||||
|
||||
it('fails loudly on unparseable content rather than passing rubbish downstream', async () => {
|
||||
mockFetch({
|
||||
ok: true,
|
||||
body: { choices: [{ message: { content: 'I think tooth 14?' } }] },
|
||||
});
|
||||
await expect(
|
||||
new OpenRouterExtractionProvider(CONFIG).extract('x', CATALOG, 'fa'),
|
||||
).rejects.toBeInstanceOf(VoiceProviderError);
|
||||
});
|
||||
|
||||
it('fails when the model returns no content at all', async () => {
|
||||
mockFetch({ ok: true, body: { choices: [] } });
|
||||
await expect(
|
||||
new OpenRouterExtractionProvider(CONFIG).extract('x', CATALOG, 'fa'),
|
||||
).rejects.toMatchObject({ stage: 'extraction' });
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user