msd-core/commands/gsd/plan-review-convergence.md at 1e3e1f7cd8dd6eca32c3ce93bb71fffea802b7ee

Files

Tom Boucher 0d6bf19bf1 fix(#4600 ): explicit --converge overrides the convergence feature gate (#4771 )

* test(#4600): pin explicit-flag-overrides-gate precedence

* fix(#4600): explicit --converge overrides the convergence feature gate

PLAN_STRATEGY=converge is set only by an explicit --converge/--cross-ai,
so gating it on workflow.plan_review_convergence made an explicit
operator flag lose to a config default and stop the run with a
question-shaped success. The config remains the default for non-flag
invocation; the flag now wins, and the step says so instead of
gate-and-exit.

* test(#4600): pin the precedence contract sentences as written

* fix(#4600): keep the precedence sentence on one line

The pinned contract phrase wrapped across a line break, so the
writer-contract assertion could not match it.

* fix(#4600): document the flag-overrides-gate precedence on user surfaces

commands/gsd/autonomous.md and docs/COMMANDS.md still said --converge
requires workflow.plan_review_convergence=true; both now state the
override. Changeset typed Changed with the docs update alongside.

* docs(#4600): backfill changeset PR number

* fix(#4600): restore the convergence gate mention in user surfaces

* test(#4600): pin the dispatched convergence run against the config gate

* fix(#4600): override the convergence gate on the dispatched run

Emitted-Drift-Ack-Growth: autonomous.md — #4600: the converge dispatch appends --override-gate inside the PLAN_STRATEGY conditional, and the precedence sentences replace the stale fail-fast instruction
Emitted-Drift-Ack-Growth: plan-review-convergence.md — #4600: config gate 1.5 honors an explicit --override-gate dispatch (token-anchored) while the standalone veto and config-get default are preserved

---------

Co-authored-by: sim <sim@local>

2026-09-15 15:53:42 -04:00

3.9 KiB

Raw Blame History

name, description, argument-hint, allowed-tools, requires

name

description

argument-hint

allowed-tools

requires

gsd:plan-review-convergence

Cross-AI plan convergence - replan until review concerns are resolved.

<phase> [--claude] [--codex] [--coderabbit] [--opencode] [--qwen] [--cursor] [--antigravity] [--agy] [--ollama] [--lm-studio] [--llama-cpp] [--kimi-code] [--text] [--ws <name>] [--all] [--max-cycles N]

Read

Write

Bash

Glob

Grep

Agent

Skill

AskUserQuestion

phase

review

autonomous

Cross-AI plan convergence loop — an outer revision gate around gsd-review and gsd-planner. Repeatedly: review plans with external AI CLIs → if HIGH or actionable non-HIGH concerns remain → replan with --reviews feedback → re-review. Stops when no unresolved HIGH concerns or actionable MEDIUM/LOW findings remain outside PLAN.md, or when max cycles is reached.

Flow: Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check unresolved HIGH + actionable non-HIGH → 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, claude, 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, run plan-phase inline (Skill at depth 0), spawn an Agent for gsd-review, check unresolved HIGH and actionable non-HIGH counts, stall detection, escalation gate.

<execution_context> @$HOME/.claude/gsd-core/workflows/plan-review-convergence.md @$HOME/.claude/gsd-core/references/revision-loop.md @$HOME/.claude/gsd-core/references/gates.md @$HOME/.claude/gsd-core/references/agent-contracts.md </execution_context>

<runtime_note> Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. Do not skip questioning steps because AskUserQuestion appears unavailable; use vscode_askquestions instead. </runtime_note>

Phase number: extracted from $ARGUMENTS (required)

Flags:

--codex — Use Codex CLI as reviewer (default if no reviewer flag given AND review.default_reviewers is unset; otherwise review.default_reviewers wins per ADR-0011 — #2315)
--agy / --antigravity — Use Antigravity CLI as reviewer
--claude — Use Claude CLI as reviewer (separate session)
--coderabbit — Use CodeRabbit as reviewer (reviews the working-tree diff, not the source tree)
--opencode — Use OpenCode as reviewer
--qwen — Use Qwen Code CLI as reviewer (Alibaba Qwen models)
--cursor — Use Cursor agent as reviewer
--ollama — Use local Ollama server as reviewer (OpenAI-compatible, default host http://localhost:11434; configure model via review.models.ollama)
--lm-studio — Use local LM Studio server as reviewer (OpenAI-compatible, default host http://localhost:1234; configure model via review.models.lm_studio)
--llama-cpp — Use local llama.cpp server as reviewer (OpenAI-compatible, default host http://localhost:8080; configure model via review.models.llama_cpp)
--kimi-code — Use Kimi Code CLI as reviewer (Moonshot AI)
--all — Use all available CLIs and running local model servers
--max-cycles N — Maximum replan→review cycles (default: 3)

Feature gate: This command requires workflow.plan_review_convergence=true. Enable with: gsd config-set workflow.plan_review_convergence true. A dispatch carrying --override-gate — how /gsd:autonomous --converge invokes this workflow (#4600) — bypasses the gate for that run.

Execute end-to-end. Preserve all workflow gates (pre-flight, revision loop, stall detection, escalation).

3.9 KiB Raw Blame History

3.9 KiB

Raw Blame History