Repository navigation
Review large workbench packages completely in bounded batches - #48
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR #45's published mind-map bundle contains 3.2 MiB and 1.1 MiB JavaScript files, which the old per-file gate rejected before review. Review complete installed text in bounded overlapping batches instead, keeping every dependency module and eliminating prefix truncation.
Every batch receives shared submission/manifest context, validates references against its actual slice, and must complete successfully; any blocking verdict or incomplete batch prevents approval. Bound total material, batch count, serialized evidence and total request size; use at most three model calls concurrently. Document timeout and static-analysis limits.
Validation: catalog validation and 97 tests pass, including complete coverage of long single lines, surrogate-safe overlap, cross-boundary suspicious code, shared context, batch limits and blocking aggregation. The real #45 release contains 17 evidence files / 5,127,318 characters and produces 25 batches before source/submission context.