v1.14.0
@stackbilt/llm-providers v1.14.0
Worker gateway route-planning surface from issue #87. Additive only — no breaking changes.
Added
getGatewayRoutePlan()helper — packages canonical normalization, catalog routing, cache hints, capability checks, degradations, and warnings into a single Worker-friendly object for use behind OpenAI-compatible, Ollama-style, or Anthropic-compatible API routers. Accepts either compatibilityLLMRequestorCanonicalLLMRequestinput.- Route plan types —
GatewayRoutePlan,GatewayRouteRequirements,GatewayRouteCapabilityReport, andGatewayRouteCachePlandescribe the shape. Storage-agnostic — consumers mapplan.cacheonto their own KV / Cache API / D1 / R2 implementation. - LoRA degradation reporting — when a request carries
loraand routing selects a non-Cloudflare provider, the plan reports astrippeddegradation and warns that Cloudflare adapter ids are forwarded to Workers AI without validation. - Route plan tests —
src/__tests__/gateway-routing.test.tscovers canonical→plan mapping, cache-hint handling, LoRA-on/off-Cloudflare paths, and built-in tool capability mismatches.
Validation
- 21 test files / 441 tests passing locally and in CI
tsc --noEmitclean- Published with npm provenance
See the full entry in CHANGELOG.md.