LearnNewsExamplesServices
Frontmatter
id11904
titlePilot cycle-aware pr-review density compression
stateClosed
labels
documentationenhancementairefactoringarchitecturemodel-experience
assigneesneo-gpt
createdAtMay 24, 2026, 3:49 PM
updatedAtMay 24, 2026, 4:47 PM
githubUrlhttps://github.com/neomjs/neo/issues/11904
authorneo-gpt
commentsCount0
parentIssue11605
subIssues[]
subIssuesCompleted0
subIssuesTotal0
blockedBy[]
blocking[]
closedAtMay 24, 2026, 4:47 PM

Pilot cycle-aware pr-review density compression

Closed v13.0.0/archive-v13-0-0-chunk-13 documentationenhancementairefactoringarchitecturemodel-experience
neo-gpt
neo-gpt commented on May 24, 2026, 3:49 PM

Context

#11605 needs bounded pilot children after the skill-runtime baggage inventory. #11902 / PR #11903 established the baseline: .agents/skills/pr-review/references/pr-review-guide.md is the largest measured hotspot at 56,962 bytes, and pr-review is the most visible source of operator friction around full-review-per-cycle bloat.

Duplicate / adjacency sweep:

  • #10537 and its closed children (#10540, #10614) handled an earlier pr-review modularization slice and measurement methodology, not the current cycle-aware full-review versus micro-delta contract.
  • #11902 is the inventory child, not the pilot implementation.
  • #11605 is the parent program and explicitly calls for a pr-review pilot.

The Problem

The current review substrate can push agents toward repeating full formal reviews after every small author delta. That preserves rigor in form while destroying focus-window quality in practice: PR conversations become long context-drain artifacts, and future reviewers must parse historical walls to find the current blocker.

The operator direction is specific: one full review can be appropriate, but later cycles should become tight micro-delta re-reviews unless the author materially changes scope. The existing substrate already contains a follow-up template, but the hot path still lets routine review cycles expand into full-review ceremony.

The Architectural Reality

pr-review is an agent skill consumed directly by reviewers. Its router should stay small; heavy procedure belongs in referenced payloads, and rare branches belong behind trigger pointers per ADR 0007, ADR 0008, and the recursive Map-vs-Atlas discipline shipped in #11319.

The pilot must reduce loaded review-cycle surface without weakening merge gates: CI-green before formal review, exact-head verification, close-target audit, evidence audit, and formal GitHub review state still matter. The compression target is repeated prose and cycle-N ceremony, not epistemic rigor.

The Fix

Pilot a narrow pr-review compression pass focused on review-cycle density:

  • Make the full-review versus follow-up-review decision explicit and cheap to apply.
  • Make cycle-N reviews default to a compact delta contract when prior context and scope boundaries are known.
  • Move historical anchors, rare branches, and examples behind trigger pointers instead of inline runtime prose.
  • Remove or compress redundant sections that restate gates already enforced elsewhere, while preserving reviewer-side V-B-A.
  • Keep graph-ingestion metric tags mechanically valid.

Contract Ledger Matrix

Target Surface Source of Authority Proposed Behavior Fallback Docs Evidence
Cycle-1 review contract #11605, #11902 inventory, pr-review skill First substantive review still uses the full template when cold-cache or broad scope requires it Existing full-review template remains .agents/skills/pr-review/** Template lint / review-body lint still passes
Cycle-N review contract Operator direction + existing follow-up template Warm-cache narrow deltas use compact micro-delta follow-up shape Full review allowed when scope broadens or context is cold pr-review guide/template payloads A focused PR demonstrates reduced payload while preserving required anchors
Historical/provenance payload ADR 0007 / ADR 0008 / #11319 Incident stories move behind trigger pointers or atlas payloads Inline prose remains only where load-bearing pr-review references/audits Byte-count delta plus reviewer usability check
Evaluation metric anchors Retrospective ingestion contract Required [ARCH_ALIGNMENT] etc. anchors remain mechanically present lint-pr-review-body catches missing anchors pr-review assets Existing/new lint passes

Decision Record impact

Aligned with ADR 0007 and ADR 0008. No ADR amendment expected unless implementation discovers a broader skill-shape rule gap.

Acceptance Criteria

  • Reduce or justify the loaded pr-review hot-path surface using #11902's measurement baseline.
  • Preserve the full-review template path for Cycle 1, cold-cache, major scope change, or lost-anchor recovery.
  • Make Cycle-N / warm-cache re-reviews use a compact micro-delta contract by default when prior context is grounded and the author delta is narrow.
  • Preserve required graph-ingestion anchors and formal GitHub review state requirements.
  • Remove, move, or compress stale historical anchors and repeated review-cycle ceremony that no longer belongs inline.
  • Provide before/after byte counts for changed pr-review payloads.
  • Run the relevant skill/template lint and at least one representative review-body lint fixture or documented equivalent.
  • Cross-family review confirms the resulting workflow is easier to scan and does not weaken review rigor.

Out of Scope

  • Rewriting every skill.
  • Changing the pull-request author workflow; that is #11605 AC5.
  • Removing CI-green or exact-head verification gates.
  • Deleting incident history; move it to better substrate if it remains useful.
  • Changing Retrospective daemon metric tags.

Avoided Traps

  • Adding another long anti-bloat section to fight bloat.
  • Treating byte reduction as success if reviewers lose the actual merge-blocking signals.
  • Reopening the entire PR-review philosophy instead of piloting the hottest measured surface.
  • Making cycle-N reviews too terse for graph ingestion or author actionability.

Related

Parent: #11605 Depends on / informed by: #11902, PR #11903 Related prior compression work: #10537, #10540, #10614

Origin Session ID: 967e325b-d90a-43f4-9e91-c212e9bda746

Retrieval Hint: pr-review cycle-aware density compression micro-delta follow-up template full review bloat skill-runtime-baggage-inventory

tobiu referenced in commit c2932a3 - "feat(pr-review): compress cycle-aware review hot path (#11904) (#11911) on May 24, 2026, 4:47 PM
tobiu closed this issue on May 24, 2026, 4:47 PM