Repository navigation
feat(agents): soft per-skill turn limits for sub-agents - #1553
Draft
ian-at-strix wants to merge 1 commit into
Draft
ian-at-strix wants to merge 1 commit into
ian-at-strix wants to merge 1 commit into
Conversation
run_strix_scan(subagent_turn_limits={skill: turns}) gives each sub-agent the
smallest limit among its skills. The agent is warned 10 turns before the limit
and reminded every 5 turns past it, but never stopped.
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
run_strix_scan(subagent_turn_limits={"pr_review/investigator": 25, ...})gives each sub-agent the smallest limit among its skills (bare or qualified names). The agent is warned 10 turns before the limit and reminded every 5 turns past it, but never stopped. Each notice is logged to run.log ("Turn-limit notice for agent ...").Replaces the frontmatter-based nudge in #1549, so the caller can set different limits per scan depth.
Known gap: the count is per run cycle, so it restarts if an agent's run restarts (e.g. after compaction).