proposal: post-plan enrichment swarm via git-as-state-machine#58
Merged
neoneye merged 3 commits intoPlanExeOrg:mainfrom Feb 21, 2026
Merged
Conversation
neoneye
added a commit
that referenced
this pull request
Mar 9, 2026
Pre-planning LLM call that scores the initial prompt on 6 quality dimensions (objective clarity, scope, constraints, stakeholders, success criteria, context) and rewrites weak prompts as flowing prose before the pipeline runs. - New boost_initial_prompt.py with PromptQualityAssessment schema - Add BOOST_INITIAL_PROMPT_RAW/MARKDOWN to FilenameEnum - Add BoostInitialPromptTask to pipeline (depends on SetupTask) - Wire into FullPlanPipeline Co-Authored-By: Claude Opus 4.6 <[email protected]>
3 tasks
1 task
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Proposes using git commits as the state machine for the post-plan enrichment swarm.
Each agent commits its output. Git log = state. Orchestrator checks commits, runs pending agents, repeats.
Key properties: durable, resumable, auditable, human-reviewable between steps.
Details in docs/proposals/git-state-machine-enrichment.md