Skip to Content

Tracing

Every context query produces trace entries that record what was accessed, when, and by what version. Traces provide a provenance chain from knowledge through to agent action.

What is traced

FieldDescription
document_idWhich document was accessed
versionWhich version was served
checkpointThe checkpoint at the time of access
accessed_atTimestamp
selectorThe query that triggered this access
result_hashSHA-256 hash of the returned content

Source node traces

Source node traces include additional fields:

FieldDescription
transportTransport type used (mcp, rest, cli, file)
serverServer name
toolTool name called
cache_hitWhether the result was served from cache
cache_ageAge of cached result in seconds

Provenance chain

Traces enable full provenance reconstruction:

“The agent resolved pack:sprint.standup → read 3 static docs at checkpoint 12 → hydrated sources/current-sprint-tickets via Jira MCP (cache miss, result hash sha256:9f1b...) → hydrated sources/recent-pr-activity via GitHub MCP (cache hit, 4m old) → generated summary.”

Design note

The trace records result_hash, not result_content. The trace proves what was seen without storing the full payload in the vault. Implementations requiring full result retention for compliance should store results in an external audit log.

Last updated on