agentbelt-sampler

agentbelt-sampler

Agent-aware span sampling: always keep errors, cost/latency outliers, retries, and novel calls; sample everything else at a low rate. Part of the agentbelt suite.

pip install agentbelt-sampler
# or, for the real OpenTelemetry Sampler adapter:
pip install agentbelt-sampler[otel]

Quickstart

from agentbelt_sampler import Sampler, SamplingPolicy, Span

sampler = Sampler(SamplingPolicy(boring_sample_rate=0.05))

if sampler.should_keep(Span(tool="search", cost_usd=0.002, is_error=False)):
    export(span)

Run python examples/volume_demo.py for a concrete before/after number (errors and outliers 100% retained, overall volume cut substantially on a repetitive synthetic stream).

What did this actually catch?

print(sampler.impact_report())
# 100 span(s) seen, 11 kept (89.0% reduction)

The most direct of the three impact reports — seen vs. kept, mapped straight to observability-backend cost reduction.

See the suite README for the full concept and how this fits with agentbelt-budget and agentbelt-loop.

License

MIT