Ajay Krishnan
51dceee224
Replace the abandoned llms-txt-mcp/Chroma docs backend with an in-repo MCP service: SQLite WAL + FTS5 + sentence-transformer embeddings, transactional source replacement, persisted state across restarts, singleflight refresh with conditional requests, hybrid lexical/semantic ranking with exact-duplicate collapse, source/host filters, and explicit-by-default content retrieval. Add docs_rebuild and a docs-rebuild CLI command. Add deterministic llms-full.txt snapshot generation for machine-local menus with hash-validated provenance manifests; lifecycle commands promote a local menu to its snapshot only when the manifest validates. Switch public source profiles to content-bearing llms-full.txt feeds. Improve web search: bounded provider fallback with per-attempt diagnostics and cancellation, an optional Brave Search API provider, strict SearXNG engine selection, capped link/media extraction, and a real engine=browser renderer that routes every request through the existing SSRF vetting while blocking WebSockets, non-GET traffic, and private destinations. Extend release checks with offline unit suites and isolated candidate container tests for both images.
64 lines
2.3 KiB
JavaScript
64 lines
2.3 KiB
JavaScript
const DEFAULT_TIMEOUT_MS = 15_000;
|
|
const MAX_ERROR_LENGTH = 240;
|
|
|
|
export function classifyProviderError(error) {
|
|
const message = error instanceof Error ? error.message : String(error);
|
|
const lower = message.toLowerCase();
|
|
let category = "provider_error";
|
|
if (lower.includes("timed out") || lower.includes("timeout")) category = "timeout";
|
|
else if (lower.includes("429") || lower.includes("rate limit")) category = "rate_limited";
|
|
else if (lower.includes("captcha") || lower.includes("challenge")) category = "blocked";
|
|
else if (lower.includes("403") || lower.includes("401") || lower.includes("denied")) category = "forbidden";
|
|
else if (lower.includes("network") || lower.includes("fetch") || lower.includes("socket")) category = "network";
|
|
return { category, message: message.replace(/\s+/g, " ").slice(0, MAX_ERROR_LENGTH) };
|
|
}
|
|
|
|
export async function attemptProvider(provider, query, limit, lang, options = {}) {
|
|
const timeoutMs = Math.max(10, Math.min(options.timeoutMs || DEFAULT_TIMEOUT_MS, 60_000));
|
|
const now = options.now || (() => performance.now());
|
|
const started = now();
|
|
if (provider.configured === false) {
|
|
return {
|
|
items: [],
|
|
diagnostic: { provider: provider.name, status: "unavailable", duration_ms: 0, result_count: 0 }
|
|
};
|
|
}
|
|
let timer;
|
|
const controller = new AbortController();
|
|
try {
|
|
const items = await Promise.race([
|
|
provider.search(query, limit, lang, controller.signal),
|
|
new Promise((_, reject) => {
|
|
timer = setTimeout(() => {
|
|
controller.abort(new Error(`provider timed out after ${timeoutMs}ms`));
|
|
reject(new Error(`provider timed out after ${timeoutMs}ms`));
|
|
}, timeoutMs);
|
|
})
|
|
]);
|
|
const bounded = Array.isArray(items) ? items.slice(0, limit) : [];
|
|
return {
|
|
items: bounded,
|
|
diagnostic: {
|
|
provider: provider.name,
|
|
status: bounded.length ? "success" : "empty",
|
|
duration_ms: Math.max(0, Math.round(now() - started)),
|
|
result_count: bounded.length
|
|
}
|
|
};
|
|
} catch (error) {
|
|
return {
|
|
items: [],
|
|
diagnostic: {
|
|
provider: provider.name,
|
|
status: "error",
|
|
duration_ms: Math.max(0, Math.round(now() - started)),
|
|
result_count: 0,
|
|
error: classifyProviderError(error)
|
|
}
|
|
};
|
|
} finally {
|
|
controller.abort();
|
|
clearTimeout(timer);
|
|
}
|
|
}
|