Skip to main content
Glama
Observability Replay

Observability Replay

by ALIBCJH

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OBS_BACKENDNoSelect the observability adapter. Use "prometheus" for a Prometheus-compatible backend; with no backend configured the server plays a scripted demo incident.demo
OBS_PROM_URLNoPrometheus base URL, e.g. http://localhost:9090. Required when using the prometheus adapter.
OBS_PROM_TOKENNoOptional bearer token for Prometheus.
OBS_SLO_P95_MSNoFleet-wide p95 latency objective in milliseconds.500
OBS_PROM_CHANGESNoSet to "off" to skip the rollout lookup if kube-state-metrics is not scraped.on
OBS_PROM_MATCHERSNoOptional label matchers for every graph query, e.g. cluster="prod".
OBS_PROM_RESOURCESNoSet to "off" to skip CPU and memory metrics if cAdvisor and kube-state-metrics are not scraped.on
OBS_SLO_AVAILABILITYNoFleet-wide availability objective as a percentage.99.9
OBS_PROM_GRAPH_PREFIXNoMetric prefix for service graph metrics.traces_service_graph_request
OBS_PROM_WORKLOAD_LABELNoLabel on container metrics that equals the service name.container
OBS_PROM_LATENCY_HISTOGRAMNoLatency histogram metric name without the _bucket suffix.<prefix>_server_seconds
OBS_PROM_WORKLOAD_MATCHERSNoOptional label matchers for every container and rollout query, e.g. namespace="shop".

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources