7. Sun
|
1e9fbd216f
|
fix(searchCache): ttlMs=0 now bypasses inflight coalescing too (#1178)
Integrated into release/v3.6.5 — correctness fix for ttlMs=0 cache bypass + cacheTTLMs ?? operator. Added 6 unit tests covering concurrent bypass, hits counter, no-store behavior, and the nullish coalescing semantic.
|
2026-04-12 21:33:05 -03:00 |
|
Regis
|
564e983c68
|
feat(search): add unified web search routing with 5 providers
Add POST /v1/search — a unified search endpoint routing queries across
5 providers (Serper, Brave, Perplexity Search, Exa, Tavily) with
automatic failover, in-memory caching, and request coalescing.
No open-source AI gateway offers unified search routing. This chains
free tiers for 5,500+ searches/month with zero downtime.
Providers: Serper ($0.001/q, 2500/mo free), Brave ($0.005/q, 1000/mo),
Perplexity Search ($0.005/q), Exa ($0.007/q, 1000/mo), Tavily
($0.008/q, 1000/mo). Auto-select picks cheapest with credentials.
Architecture follows existing patterns:
- searchRegistry.ts (same as embeddingRegistry.ts)
- search.ts handler (same as embeddings.ts)
- route.ts (same as /v1/embeddings/route.ts)
- searchCache.ts (bounded TTL cache + request coalescing)
Schema finalized — all future fields defined as optional with safe
defaults. No breaking changes when implementing content extraction,
answer synthesis, or ranking.
Key features:
- Per-provider request builders and response normalizers
- Enriched response: display_url, score, favicon_url, content block,
metadata, answer block, errors array, upstream_latency_ms metrics
- Cost-sorted auto-select with failover on 429/5xx/timeout
- Credential fallback (perplexity-search reuses perplexity chat key)
- Cache key includes all result-affecting parameters
- max_results clamped to provider limits, sanitized error responses
- Factored validators (validateSearchProvider factory)
- CORS headers on all responses
- Dashboard: Search & Discovery section, search provider template
- DB migration 007: request_type column in call_logs
- 28 unit tests (registry, cache, coalescing, validation)
|
2026-03-17 18:28:35 +01:00 |
|