TelemetryReporter from @agentvault/crypto.
What Telemetry Powers
AgentVault uses ingested spans to:- Compute trust scores — reliability, error rate, and response time dimensions feed into the agent’s trust tier
- Populate the observability dashboard — trace visualization, span timelines, and aggregate metrics
- Feed external collectors — the OTel push export worker forwards spans to any OTLP-compatible backend
Telemetry is agent-scoped. Every ingest request is tied to a hub identity, and all data is
tenant-isolated at the database level via Row-Level Security.
Ingest Endpoint
Request Body
Response
Authentication
The ingest endpoint accepts three authentication methods.- API Key (Recommended)
- Device JWT
- Clerk JWT
Best for agents using Or equivalently via the
@agentvault/client or any external process. Generate an API key
from the AgentVault dashboard under Agent > API Keys.Authorization header:Span Format
The endpoint accepts OTLP camelCase field names. Both nanosecond Unix timestamps (startTimeUnixNano) and ISO 8601 strings (start_time) are supported.
Semantic Conventions
Use theai.agent.* namespace for all agent-specific attributes. These conventions power
AgentVault’s trust scoring and observability pipeline.
LLM Calls
LLM Calls
Tool Invocations
Tool Invocations
Errors
Errors
Tasks
Tasks
Messages
Messages
Span Status Codes
Span Status Codes
Integration Examples
Choose between the built-in SDK (recommended) or wiring up the standard OTel SDK directly.Built-in SDK (Recommended)
If your agent uses@agentvault/crypto or @agentvault/client, the TelemetryReporter class
handles span building, OTLP serialization, buffering, and automatic periodic flushing in one object.
Standard OTel SDK
Use the standard OpenTelemetry SDK with a custom exporter that posts to AgentVault’s ingest endpoint.1
Install dependencies
2
Create a custom exporter
3
Initialize the tracer and report spans
Query API
Once spans are ingested, retrieve them via the query endpoints (owner auth required).
The
/summary endpoint returns aggregate metrics — total spans, error count, error rate, and
average duration — useful for quick health checks.
Rate Limits
The built-inTelemetryReporter buffers spans and flushes them in one POST every 30 seconds,
keeping you safely under the limit without any manual batching.