fix(resolve-pr-feedback): unblock /loop scheduling#582
Merged
Conversation
…works The disable-model-invocation flag blocks the Skill tool for any model-initiated invocation, including scheduled re-entry from /loop. Only a user typing the slash command bypasses it. That defeats scheduled PR-comment resolution, which is a legitimate use case. Drop the flag and document the tradeoff in the plugin AGENTS.md so non-beta skills don't reintroduce it. Description specificity and the required PR argument remain as guards against accidental auto-fire.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
/loopcouldn't schedule/resolve-pr-feedbackbecausedisable-model-invocation: trueblocks the Skill tool for every model-initiated invocation, not just semantic auto-fire. A scheduled wake-up is model-initiated, so the agent fell back to "follow the steps manually" and the skill never ran.Remove the flag. The description is already intent-specific ("addressing PR review comments, resolving review threads"), and the skill body requires a PR context with
ghauth, so accidental auto-fire stays bounded. PluginAGENTS.mdnow documents the/looptradeoff so non-beta skills don't reintroduce the flag.