Instruct planning agents to summarize the plan at end of turn - #373
Merged
Conversation
Extend the shared PLAN_WRITTEN responsibility (single-sourced in PlannedWorkflow) to tell the agent to post a concise summary of the plan in chat when ending its planning turn, so the user can review without opening the plan.md artifact. This propagates to every plan-generating workflow (github-peer-reviewed, github-self-reviewed, local-git-self-reviewed, github-dependabot) via the shared reference and renders in both the workflow overview and the per-turn briefing. Regenerate the golden briefing fixtures and lock the wording in with a briefing assertion. Co-Authored-By: Claude Opus 4.8 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Extend the shared
PLAN_WRITTENresponsibility (single-sourced inPlannedWorkflow) to tell the agent to post a concise summary of the plan in chat when ending its planning turn, so the user can review the plan without opening theplan.mdartifact.Why
Every plan-generating workflow references the same
PlannedWorkflow.PLAN_WRITTENobject, so a single edit propagates the instruction to all of them —github-peer-reviewed,github-self-reviewed,local-git-self-reviewed, andgithub-dependabot— and it renders in both the workflow overview (system prompt) and the per-turn briefing.Changes
workflows/planned_workflow.py: append the summarize instruction toPLAN_WRITTEN.description(and its doc comment).github_peer_reviewed_system_prompt.md,github_peer_reviewed_state_PLANNING.md).tests/core/test_briefing.py: assert the PLANNING briefing mentions summarizing the plan.No new responsibility (not a gate) — so no orchestrator, state-machine, store, MCP, or migration changes.
🤖 Generated with Claude Code