Atlas seed-harvest pipeline (Tier 1-3, approval artifact, sync)#100
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds the Atlas seed-harvest pipeline end to end:
atlas-harvestCLI driver, CI prettier coverage.Code review
Driven through a 13-round multi-agent CR loop (16 reviewers per round across code-review, silent-failure, test-coverage, comment-accuracy, and type-design lenses), with 12 fix rounds (fix2–fix13). Behavioral must-fix trajectory over the final rounds: 8 → 4 → 2 → 0, certified at R13 (folds-only final round verified by an exhaustive diff-audit gate). Full found/fixed/deferred audit manifests are retained locally (
~/.claude/specs/2026-06-09-atlas-r*.md).Accepted residuals (deliberate deferrals)
Documented per-line in the R13 manifest §f; headline classes: HTTP/LLM client timeouts, 409 idempotency detection by substring, empty-date fallbacks (
??), non-atomic manifest writes, hand-mirrored enum sets, heuristic distillation/capture tuning (markdown edge cases), non-Latin tokenization in the dedup gate (mark-only), symlink blind spots in the validation walk, and S20-coupled items (/api/searchroute, webhook key-grammar unification, cross-run key stability under fusion).Test plan
tsc --noEmitclean on both configs (build + scripts)npm run buildgreen