From c036e4cc60cb32e13c9dd8971e9e11025ff93a78 Mon Sep 17 00:00:00 2001 From: Alex Verkhovsky Date: Mon, 2 Mar 2026 16:58:45 -0700 Subject: [PATCH] fix(quick-flow): use human-in-the-loop fallback for review without subagents Sequential inline reviews in the same context suffer from anchoring bias and context blowout. Instead, generate separate review prompt files and ask the human to run each in a separate session. --- .../bmad-quick-flow/quick-dev2/steps/step-04-review.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-04-review.md b/src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-04-review.md index e7b6d9315..d9ebbc182 100644 --- a/src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-04-review.md +++ b/src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-04-review.md @@ -29,7 +29,7 @@ Do NOT `git add` anything — this is read-only inspection. **One-shot:** Skip diff construction. Still invoke `{adversarial_review_task}` in a subagent with the changed files — inline review invites anchoring bias. -**Plan-code-review:** Launch three subagents without conversation context. If no sub-agents are available, perform all three reviews inline sequentially. +**Plan-code-review:** Launch three subagents without conversation context. If no sub-agents are available, generate three review prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings. - **Blind hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via `{adversarial_review_task}`. - **Edge case hunter** — receives `{diff_output}` and read access to the project. Invoke via `{edge_case_hunter_task}`.