averello/compound-engineering-plugin-mirror
1
0
Fork 0
mirror of https://github.com/EveryInc/compound-engineering-plugin.git synced 2026-06-19 15:41:46 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat(ce-review): add recommended-action tie-breaking to Stage 5 merge

Browse Source 
When contributing reviewers imply different per-finding actions for the same
merged finding (e.g., correctness says Apply via suggested_fix, testing says
Skip via low confidence), synthesis now picks the most conservative action
using Skip > Defer > Apply > Acknowledge.

This makes the walk-through's recommended action stable across re-runs and
makes LFG results auditable after the fact. The user can still override per
finding — the rule only determines what gets labeled "recommended."

Part of the Interactive judgment-loop redesign (Unit 1 of 8).
This commit is contained in:
Trevin Chow
2026-04-17 21:41:53 -07:00
parent 0a18b8556e
commit fedbf64d82
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plugins/compound-engineering/skills/ce-review/SKILL.md
+1
View File
@@ -469,6 +469,7 @@ Convert multiple reviewer compact JSON returns into one deduplicated, confidence
5. **Separate pre-existing.** Pull out findings with `pre_existing: true` into a separate list.
6. **Resolve disagreements.** When reviewers flag the same code region but disagree on severity, autofix_class, or owner, annotate the Reviewer column with the disagreement (e.g., "security (P0), correctness (P1) -- kept P0"). This transparency helps the user understand why a finding was routed the way it was.
7. **Normalize routing.** For each merged finding, set the final `autofix_class`, `owner`, and `requires_verification`. If reviewers disagree, keep the most conservative route. Synthesis may narrow a finding from `safe_auto` to `gated_auto` or `manual`, but must not widen it without new evidence.
7b. **Tie-break the recommended action.** Interactive mode's walk-through and LFG paths present a per-finding recommended action (Apply / Defer / Skip / Acknowledge) derived from the normalized `autofix_class` and `suggested_fix`. When contributing reviewers implied different actions for the same merged finding, synthesis picks the most conservative using the order `Skip > Defer > Apply > Acknowledge`. This guarantees that identical review artifacts produce the same recommendation deterministically, so LFG results are auditable after the fact and the walk-through's recommendation is stable across re-runs. The user may still override per finding via the walk-through's options; this rule only determines what gets labeled "recommended."
8. **Partition the work.** Build three sets:
- in-skill fixer queue: only `safe_auto -> review-fixer`
- residual actionable queue: unresolved `gated_auto` or `manual` findings whose owner is `downstream-resolver`