Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.asymptotelabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

Schema Normalization

Beacon normalizes OTLP attributes and hook payloads into the same endpoint contract. The collector exporter looks for common runtime fields, while hook telemetry builds those fields directly from hook payloads.

Source mapping

Source signalNormalized field or action
gen_ai.request.modelmodel
gen_ai.tool.nametool.name
mcp.tool.namemcp.tool
process.command_linecommand.command
file.pathfile.path
conversation.idsession.id
vcs.repository.urlrepository
git.branchbranch
Prompt-like eventsprompt.submitted
Shell or exec eventscommand.executed
MCP eventsmcp.tool_invoked
File, write, or edit eventsfile.modified
Approval eventsapproval.requested
Other tool activitytool.invoked

Category inference

When a runtime omits event.category, Beacon infers it from event.action:
Action patternInferred category
prompt.*prompt
command.*command
file.*file
mcp.*mcp
approval.* or policy.*approval
metric.*metric
tool.*tool

Endpoint event schema

Return to the schema overview.

Schema fields

Review entities, optional context, and shared top-level fields.

Telemetry pipeline

See where normalization fits in the local telemetry flow.