Repository navigation
Conversation
Adds LABS_GUARDRAIL_ENFORCE (default false). When enabled, a block verdict from the before_tool webhook stops the tool call in both the chat assistant and the background agent loop. Default behaviour is unchanged (passive, observe-only).
Webhooks can apply a different rule per agent, and a blocked tool is skipped only when enforcement is on.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
LABS_GUARDRAIL_ENFORCE(default false) so a Labs webhook{"verdict":"block"}can skip the tool on a local or self-hosted instance. With the flag off, the tool still runs, so Guardrail 101 and Carte Noire stay valid.agent_nameto the hook envelope so a webhook can apply different rules per agent. The field is additive; webhooks that ignore unknown JSON fields are unaffected.Closes #617
Test plan
uv run pytest tests/unit/labs/test_guardrail_service.py tests/unit/labs/test_guardrail_enforce_chat.pyLABS_GUARDRAIL_ENFORCE=true, a webhook that returns{"verdict":"block"}onbefore_toolskips the toolagent_namewhen the caller passes one