fix: restore swarm preference and add default_swarm_mode - #105
Merged
Merged
Conversation
The 0.39.1 upstream sync stripped the proactiveness/action directives from both engines' system prompts (upstream MoonshotAI#3028) and made swarm mode per-session (upstream MoonshotAI#3433), which left the agent preferring sequential Agent subagent tasks over the parallel AgentSwarm tool even with swarm mode enabled, and the task path appeared to ignore coding standards. Restore the removed directives and add explicit swarm-preference and subagent-rules guidance to both system prompts, and add a default_swarm_mode config option (v1 + v2 engines + protocol) so new sessions can start in swarm mode.
5 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related Issue
default_swarm_moderequest.Problem
After the 0.39.1 upstream sync, the fork prefers spawning sequential
Agentsubagent tasks over the parallelAgentSwarmtool even when the swarm-mode toggle is on, and the task path appears to ignore coding standards / AGENTS.md rules. The sync's MoonshotAI#3028 removed the "default to taking action / make real changes / deliver the complete change" directives from both engines' system prompts, and MoonshotAI#3433 documents that swarm/goal toggles are now per-session (the button does not persist).What changed
system.mdfiles.AgentSwarmover a single sequentialAgentfor decomposable work, and to carry coding-standards/AGENTS.md reading into every subagent prompt.default_swarm_modeconfig option (v1 + v2 engines + protocol) so new sessions can start in Swarm mode, mirroringdefault_plan_mode.defaultSwarmModebootstrap tests; regenerate the config manifest; document the option (en/zh); add a changeset and a fork patch row.Checklist