golem15/msd-core
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(#936): run plan-phase inline in convergence; guard against nested spawner wraps (#939)

Browse Source 
Both sites in plan-review-convergence.md that wrapped gsd-plan-phase in
Agent() (initial planning + replan loop) are now bare Skill() calls at depth 0.
On Claude Code, a depth-1 Agent has no Agent tool so wrapped plan-phase could
never spawn gsd-planner/gsd-plan-checker — the replan loop silently produced no
revised plan when HIGHs were found. Running plan-phase inline from the depth-0
orchestrator (which retains the Agent tool) restores the full sub-agent chain.

A full audit of all workflow files confirmed these two sites were the only
instances of the anti-pattern (no other workflow wraps a spawner orchestrator
in Agent() without a RUNTIME carve-out).

Added structural guard test bug-936-no-nested-spawner-wrap.test.cjs that
dynamically derives the spawner set (workflows containing subagent_type=) and
asserts no workflow wraps a spawner inside Agent() without a RUNTIME != claude
carve-out — prevents silent regression. Test passes on fixed code, would fail
on pre-fix code at the two de-wrapped sites.

Also applied two low-severity prose nits flagged in review:
- commands/gsd/plan-review-convergence.md: orchestrator role updated to
  describe inline plan-phase + Agent for review (was generic "spawn Agents")
- gsd-core/workflows/plan-review-convergence.md success_criteria: narrowed
  "Each Agent fully completes" to the review Agent (plan-phase is inline now)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-06-09 12:37:32 -04:00
committed by GitHub
parent dcb0d8a28d
commit e4e8a9fcb8
5 changed files with 326 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
commands/gsd/plan-review-convergence.md
View File

@@ -17,11 +17,11 @@ requires: [phase, review]
Cross-AI plan convergence loop — an outer revision gate around gsd-review and gsd-planner.
Repeatedly: review plans with external AI CLIs → if HIGH concerns found → replan with --reviews feedback → re-review. Stops when no HIGH concerns remain or max cycles reached.
**Flow:** Agent→Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check HIGHs → Agent→Skill("gsd-plan-phase --reviews") → Agent→Skill("gsd-review") → ... → Converge or escalate
**Flow:** Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check HIGHs → Skill("gsd-plan-phase --reviews") → Agent→Skill("gsd-review") → ... → Converge or escalate
Replaces gsd-plan-phase's internal gsd-plan-checker with external AI reviewers (codex, gemini, etc.). Each step runs inside an isolated Agent that calls the corresponding existing Skill — orchestrator only does loop control.
Replaces gsd-plan-phase's internal gsd-plan-checker with external AI reviewers (codex, gemini, etc.). Plan-phase runs **inline** (bare Skill at depth 0) so it can spawn gsd-planner/gsd-plan-checker at depth 1. Review runs inside an isolated Agent (gsd-review is a Bash leaf — no sub-agents needed). Orchestrator only does loop control.
**Orchestrator role:** Parse arguments, validate phase, spawn Agents for existing Skills, check HIGHs, stall detection, escalation gate.
**Orchestrator role:** Parse arguments, validate phase, run plan-phase inline (Skill at depth 0), spawn an Agent for gsd-review, check HIGHs, stall detection, escalation gate.
</objective>
<execution_context>