feat(#962): onError — infrastructure-error observability hook#22
Merged
Conversation
New listener slot on Agent that fires when an exception is about to
propagate out of an agentic invocation — LLM transport failures,
response parse failures, budget exceptions, skill-routing errors.
Pure observability: the original exception always rethrows after the
listener runs. If the listener itself throws, its failure is attached
to the original via addSuppressed so it can never silently disappear.
Distinct from `onToolError`, which is per-tool semantic recovery and
can substitute repaired arguments or a value for the failure.
API:
agent<IN, OUT>("name") {
onError { t -> log.error("agent failed", t) }
}
The listener field is settable post-construction (matches
onToolUse / onSkillChosen / onKnowledgeUsed convention) so
instrumentation can attach to a frozen agent.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
New listener slot on Agent that fires when an exception is about to propagate out of an agentic invocation — LLM transport failures, response parse failures, budget exceptions, skill-routing errors.
Pure observability: the original exception always rethrows after the listener runs. If the listener itself throws, its failure is attached to the original via addSuppressed so it can never silently disappear.
Distinct from
onToolError, which is per-tool semantic recovery and can substitute repaired arguments or a value for the failure.API:
agent<IN, OUT>("name") {
onError { t -> log.error("agent failed", t) }
}
The listener field is settable post-construction (matches onToolUse / onSkillChosen / onKnowledgeUsed convention) so instrumentation can attach to a frozen agent.