Add observability module: Spring AI built-in meters and spans, cost per endpoint from token usage, Prometheus and Grafana dashboard
Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01JXVi2GMQ7bR5EmbUFdDj7N
This commit is contained in:
@@ -0,0 +1,9 @@
|
||||
# Streaming asks for usage; a server that omits it is counted as unpriced
|
||||
|
||||
stream request body asks for usage (stream_options.include_usage): true
|
||||
request fragment: "stream":true
|
||||
|
||||
two calls to a server that omits the usage block (/ask and /stream):
|
||||
gen_ai.client.token.usage total, before 7 -> after 7
|
||||
app.ai.unpriced{reason=no-usage} for ask : 1
|
||||
app.ai.unpriced{reason=no-usage} for stream: 1
|
||||
Reference in New Issue
Block a user