@xemahq/llm-client-nest
Apache-2.0The one way a Xema service calls a model: resolve the LLM gateway from the service registry, mint a short-lived sealed grant through llm-registry-api, call it, and emit the OpenTelemetry GenAI semantic conventions — once, instead of eleven times.
100
Security score
0 known advisories in v0.16.0
Weekly downloads
—
Unpacked size
295.7 kB
Dependencies
2
Last publish
11 hours ago
Security advisories
No known vulnerabilities affect v0.16.0.