5b5bb947ef
- Add instagram-extractor.ts: yt-dlp subprocess backend for Instagram caption extraction. No in-process browser state, maintained against Instagram frontend churn, supports cookies.txt for auth-walled reels. - Add feature flag EXTRACTOR_BACKEND (ytdlp|playwright) in QueueProcessor so the old Playwright path remains available as fallback. - Add 9 unit tests and 2 live-network integration tests for the new extractor. - Dockerfile: install yt-dlp via pip3 alongside existing Chromium deps. - docker-compose: expose EXTRACTOR_BACKEND env var (default: ytdlp). Also in this commit: - LLM: configurable per-request timeout via LLM_REQUEST_TIMEOUT_MS (default 120s); set maxRetries=0 to surface errors immediately; llama-swap /running health probe. - QueueProcessor: thread progress callback through parser phase. - LlmHealthIndicator: surface llama-swap loaded-model name. - Logging: improve error serialization in queue-processor tests. - .env.example: document llama-swap endpoint and model options. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
51 lines
1.3 KiB
TypeScript
51 lines
1.3 KiB
TypeScript
import { json } from '@sveltejs/kit';
|
|
import { env } from '$env/dynamic/private';
|
|
import { checkLLMHealth, isModelLoaded } from '$lib/server/llm';
|
|
|
|
/**
|
|
* Health check endpoint for the LLM service (llama-swap on ideapad).
|
|
*
|
|
* Three states:
|
|
* - ok → endpoint reachable AND configured model is loaded in VRAM
|
|
* - warming → endpoint reachable but configured model not yet loaded
|
|
* (next request will trigger a cold load)
|
|
* - error → endpoint unreachable
|
|
*/
|
|
export async function GET() {
|
|
try {
|
|
const reachable = await checkLLMHealth();
|
|
const configuredModel = env.LLM_MODEL || 'gpt-4o';
|
|
|
|
if (!reachable) {
|
|
return json(
|
|
{
|
|
status: 'error',
|
|
message: 'LLM service is not accessible',
|
|
configuredModel
|
|
},
|
|
{ status: 503 }
|
|
);
|
|
}
|
|
|
|
const warm = await isModelLoaded(configuredModel);
|
|
return json({
|
|
status: warm ? 'ok' : 'warming',
|
|
message: warm
|
|
? `Model ${configuredModel} loaded and ready`
|
|
: `Model ${configuredModel} configured; next request will trigger a cold load`,
|
|
configuredModel,
|
|
loaded: warm
|
|
});
|
|
} catch (error) {
|
|
const errorMessage = error instanceof Error ? error.message : 'Unknown error';
|
|
return json(
|
|
{
|
|
status: 'error',
|
|
message: errorMessage,
|
|
configuredModel: env.LLM_MODEL || 'gpt-4o'
|
|
},
|
|
{ status: 500 }
|
|
);
|
|
}
|
|
}
|