Add guard/noise/git-memory to autoloop, new reason and predict workflows - #4
Merged
Merged
Conversation
autoloop: - #1: Clarify comparisons are always against original baseline - #2: Count only autoloop: commits (not Revert commits) for iteration limit - #3: Constrain guard output to GUARD_PASSED/GUARD_FAILED on first line reason: - #4: Add loop max:8 on converge step for bounded stopping - #5: Feed {{tally}} into generate-a so it gets previous winner - #6: Report uses only tally+critique instead of all 6 step outputs predict: - #7: Inline finding format in all three analyst prompts - #8: Broaden file extensions, respect user scope, exclude vendor dirs readme: - #9: Move predict/reason next to tri-* analysis group
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Ported useful patterns from autoresearch, adapted to pikit's deterministic workflow model.
autoloop.yml — rewritten
Guard:field — secondary command that must pass for changes to be kept, even if metric improvedRuns:field — run metric N times, take median (volatile benchmarks)git loghistory reading; survives session crashesgit reverton failurereason.yml — new
MODE: debate(skip synthesis)predict.yml — new
All 107 validation tests pass.