Conversation
…iewer The expert-reviewer sub-agent was inconsistently following the multi-model dispatch instructions — sometimes doing it, sometimes skipping to a single-pass review. Fix: restructure to match the msbuild pattern where the outer workflow body (review-shared.md) orchestrates the multi-model dispatch, and the expert-reviewer focuses on per-dimension analysis. Architecture: - Outer agent (review-shared.md body): dispatches 3 parallel expert-reviewer calls with opus/sonnet/gpt-5.3, collects results, runs adversarial consensus, validates line numbers, posts review - Expert-reviewer (agent.md): per-dimension sub-agents in batches of 4, returns structured findings as text (no safe-output calls) This ensures multi-model always happens (outer agent controls it) while each expert-reviewer does thorough per-dimension analysis. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Restructures the review architecture to ensure multi-model review always happens:
Before: Outer agent → single expert-reviewer → expert-reviewer told to dispatch 3 models (inconsistently followed)
After: Outer agent dispatches 3 expert-reviewers with different models → each does per-dimension analysis → outer agent runs consensus → posts results
Modeled after dotnet/msbuild's proven pattern where orchestration is in the workflow body.