Merge c036e4cc60 into efc69ffb2c

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.
2026-03-03 00:59:21 +01:00 · 2026-03-02 16:58:45 -07:00 · 2026-03-02 16:48:34 -07:00 · 2026-03-02 16:44:18 -07:00
5 changed files with 7 additions and 10 deletions
--- a/src/bmm/agents/quick-flow-solo-dev.agent.yaml
+++ b/src/bmm/agents/quick-flow-solo-dev.agent.yaml
@ -24,12 +24,12 @@ agent:
      description: "[QS] Quick Spec: Architect a quick but complete technical spec with implementation-ready stories/specs"
    - trigger: QD or fuzzy match on quick-dev
-      workflow: "{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev/workflow.md"
+      exec: "{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev/workflow.md"
      description: "[QD] Quick-flow Develop: Implement a story tech spec end-to-end (Core of Quick Flow)"
-    - trigger: QD2 or fuzzy match on quick-dev2
+    - trigger: QQ or fuzzy match on quick-dev2
-      workflow: "{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md"
+      exec: "{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md"
-      description: "[QD2] Quick Dev 2: Unified quick flow — clarify intent, plan, implement, review, present (experimental)"
+      description: "[QQ] Quick Dev 2: Unified quick flow — clarify intent, plan, implement, review, present (experimental)"
    - trigger: CR or fuzzy match on code-review
      workflow: "{project-root}/_bmad/bmm/workflows/4-implementation/code-review/workflow.yaml"
--- a/src/bmm/module-help.csv
+++ b/src/bmm/module-help.csv
@ -3,7 +3,7 @@ bmm,anytime,Document Project,DP,,_bmad/bmm/workflows/document-project/workflow.y
 bmm,anytime,Generate Project Context,GPC,,_bmad/bmm/workflows/generate-project-context/workflow.md,bmad-bmm-generate-project-context,false,analyst,Create Mode,"Scan existing codebase to generate a lean LLM-optimized project-context.md containing critical implementation rules patterns and conventions for AI agents. Essential for brownfield projects and quick-flow.",output_folder,"project context",
 bmm,anytime,Quick Spec,QS,,_bmad/bmm/workflows/bmad-quick-flow/quick-spec/workflow.md,bmad-bmm-quick-spec,false,quick-flow-solo-dev,Create Mode,"Do not suggest for potentially very complex things unless requested or if the user complains that they do not want to follow the extensive planning of the bmad method. Quick one-off tasks small changes simple apps brownfield additions to well established patterns utilities without extensive planning",planning_artifacts,"tech spec",
 bmm,anytime,Quick Dev,QD,,_bmad/bmm/workflows/bmad-quick-flow/quick-dev/workflow.md,bmad-bmm-quick-dev,false,quick-flow-solo-dev,Create Mode,"Quick one-off tasks small changes simple apps utilities without extensive planning - Do not suggest for potentially very complex things unless requested or if the user complains that they do not want to follow the extensive planning of the bmad method, unless the user is already working through the implementation phase and just requests a 1 off things not already in the plan",,,
-bmm,anytime,Quick Dev 2,QD2,,_bmad/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md,bmad-bmm-quick-dev2,false,quick-flow-solo-dev,Create Mode,"Unified quick flow (experimental): clarify intent plan implement review and present in a single workflow",implementation_artifacts,"tech spec implementation",
+bmm,anytime,Quick Dev 2,QQ,,_bmad/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md,bmad-bmm-quick-dev2,false,quick-flow-solo-dev,Create Mode,"Unified quick flow (experimental): clarify intent plan implement review and present in a single workflow",implementation_artifacts,"tech spec implementation",
 bmm,anytime,Correct Course,CC,,_bmad/bmm/workflows/4-implementation/correct-course/workflow.yaml,bmad-bmm-correct-course,false,sm,Create Mode,"Anytime: Navigate significant changes. May recommend start over update PRD redo architecture sprint planning or correct epics and stories",planning_artifacts,"change proposal",
 bmm,anytime,Write Document,WD,,_bmad/bmm/agents/tech-writer/tech-writer.agent.yaml,,false,tech-writer,,"Describe in detail what you want, and the agent will follow the documentation best practices defined in agent memory. Multi-turn conversation with subprocess for research/review.",project-knowledge,"document",
 bmm,anytime,Update Standards,US,,_bmad/bmm/agents/tech-writer/tech-writer.agent.yaml,,false,tech-writer,,"Update agent memory documentation-standards.md with your specific preferences if you discover missing document conventions.",_bmad/_memory/tech-writer-sidecar,"standards",
--- 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, implement directly. 
+**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}`.
--- a/src/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md
+++ b/src/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md
@ -71,7 +71,7 @@ This uses **step-file architecture** for disciplined execution:
 Load and read full config from `{main_config}` and resolve:
- `project_name`, `implementation_artifacts`, `user_name`
+- `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
 - `communication_language`, `document_output_language`, `user_skill_level`
 - `date` as system-generated current datetime
 - `project_context` = `**/project-context.md` (load if exists)
--- a/test/fixtures/agent-schema/valid/menu-triggers/compound-triggers.agent.yaml
+++ b/test/fixtures/agent-schema/valid/menu-triggers/compound-triggers.agent.yaml
@ -29,6 +29,3 @@ agent:
    - trigger: H or fuzzy match on help
      description: "[H] Single-word compound trigger (1-letter shortcut)"
      action: help
    - trigger: QD2 or fuzzy match on quick-dev2
      description: "[QD2] Alphanumeric shortcut with trailing digit"
      action: quick_dev2
Author	SHA1	Message	Date
Alex Verkhovsky	f22018525f	Merge `c036e4cc60` into `efc69ffb2c`	2026-03-03 00:59:21 +01:00
Alex Verkhovsky	c036e4cc60	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.	2026-03-02 16:58:45 -07:00
Alex Verkhovsky	f740cd2d17	fix(quick-flow): address PR review findings for quick-dev2 - step-04-review: fix copy-paste fallback text to say "perform all three reviews inline sequentially" instead of "implement directly" - workflow.md: add missing planning_artifacts to initialization list, matching quick-spec and quick-dev siblings - quick-flow-solo-dev.agent.yaml: change QD and QQ menu entries from workflow: to exec: for .md files, matching the exec-for-md convention	2026-03-02 16:48:34 -07:00
Alex Verkhovsky	60c5b12644	fix(quick-flow): rename QD2 trigger to QQ for schema compliance COMPOUND_TRIGGER_PATTERN only allows uppercase letters in shortcuts. Rename to QQ so quick-dev2 passes agent schema validation.	2026-03-02 16:44:18 -07:00