agestra 4.8.3 → 4.9.0

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "agestra",
       "source": "./",
       "description": "Orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
-      "version": "4.8.3",
+      "version": "4.9.0",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.8.3",
+  "version": "4.9.0",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
   "mcpServers": {
     "agestra": {

package/.gemini/commands/agestra/setup.toml

@@ -0,0 +1,12 @@
+description = "Run the Agestra setup workflow for provider selection and UI language."
+prompt = """
+You are executing the Agestra setup workflow inside Gemini CLI.
+
+Use the shared workflow spec below as the source of truth and adapt it to the current Gemini host session:
+@{commands/setup.md}
+
+Gemini-specific rules:
+- Start with `environment_check`, `provider_list`, and `setup_status`.
+- Prefer Agestra MCP tools over ad-hoc shell edits.
+- Keep all user-facing questions and the final answer in the user's language.
+"""

package/AGENTS.md

@@ -25,7 +25,7 @@ This repository includes a Codex-friendly host wrapper for Agestra.
 ## Core MCP Tools
 
 - `environment_check` and `provider_list`: inspect host/provider state first
-- `agent_debate_moderate` and `agent_debate_review`: run structured multi-provider review flows
+- `agent_debate_structured` (with `agent_debate_approve`/`_continue`/`_reject`) and `agent_debate_review`: run approval-gated multi-provider review flows
 - `cli_worker_spawn`, `agent_changes_review`, `agent_changes_accept`, `agent_changes_reject`: use for autonomous Codex/Gemini worker tasks
 - `qa_run`: verify implementation before reporting completion
 

package/GEMINI.md

@@ -28,7 +28,7 @@ Each command delegates to the shared workflow specs in `commands/*.md`.
 
 ## Core MCP Tools
 
-- `agent_debate_moderate`, `agent_debate_review`: structured multi-provider reviews and debates
+- `agent_debate_structured`, `agent_debate_approve`/`_continue`/`_reject`, `agent_debate_review`: structured multi-provider reviews and approval-gated debates
 - `cli_worker_spawn`, `agent_changes_review`, `agent_changes_accept`, `agent_changes_reject`: autonomous worker lifecycle
 - `workspace_*`: document-backed review and aggregation flows
 - `qa_run`: final verification step before completion

package/README.ja.md

@@ -164,7 +164,10 @@ Turborepo モノレポで、9 パッケージ構成です:
 | `agent_debate_create` | ターン制ディベートセッションを作成（debate ID を返す） |
 | `agent_debate_turn` | 1 プロバイダー分のターンを実行。`provider: "claude"` で Claude の独立参加も可能 |
 | `agent_debate_conclude` | ディベートを終了し、最終トランスクリプトを生成 |
-| `agent_debate_moderate` | 完全自動のディベートを実行。セッション作成、provider ラウンドの実行、専門エージェント選定の記録、合意検出を行い、要約のみ返す |
+| `agent_debate_structured` | 承認ゲート付きの構造化ディベートを開始。個別レビュー、必要に応じた別名整理、投票集計ラウンドを行い、承認されるまで合成は書かれず `ready-for-approval` で待機 |
+| `agent_debate_approve` | リーダーが `ready-for-approval` セッションを承認。合成ドキュメントを書き出してセッションを終了 |
+| `agent_debate_continue` | `ready-for-approval`（または `escalated`）セッションに追加ラウンド（3/5/10）を実行 |
+| `agent_debate_reject` | 合成を書かずに構造化ディベートセッションを却下 |
 | `agent_debate_review` | 文書を複数プロバイダーへ送り、独立したレビューを依頼 |
 | `agent_cross_validate` | 出力をクロスバリデーション（agent-tier validators のみ） |
 | `agent_changes_review` | 分離タスクでのファイル変更をレビュー |

package/README.ko.md

@@ -205,7 +205,10 @@ Turborepo 모노레포, 9개 패키지:
 | `agent_debate_create` | 턴 기반 토론 세션 생성 (토론 ID 반환) |
 | `agent_debate_turn` | 공급자 1턴 실행; `provider: "claude"`로 Claude 독립 참여 지원 |
 | `agent_debate_conclude` | 토론 종료 및 최종 트랜스크립트 생성 |
-| `agent_debate_moderate` | 완전 자동화 토론 — 세션 생성, provider 라운드 실행, Specialist 선택 기록, 가능할 때 Claude host-backed 턴에 반영, 합의 검출, 요약만 반환 |
+| `agent_debate_structured` | 승인 게이트 구조화 토론 시작 — 개별 리뷰, 선택적 별칭 정리, 투표 집계 라운드, 합성은 승인 전까지 작성되지 않음 (`ready-for-approval` 상태로 대기) |
+| `agent_debate_approve` | 리더가 `ready-for-approval` 세션을 승인하여 합성 문서를 작성하고 세션을 종료 |
+| `agent_debate_continue` | `ready-for-approval`(또는 `escalated`) 세션에 추가 라운드(3/5/10) 실행 |
+| `agent_debate_reject` | 합성 없이 구조화 토론 세션 거부 |
 | `agent_debate_review` | 문서를 여러 공급자에게 독립적으로 리뷰 요청 |
 | `agent_cross_validate` | 출력 교차 검증 (에이전트 등급 검증자만 가능) |
 | `agent_changes_review` | 격리된 작업의 파일 변경 리뷰 |

package/README.md

@@ -205,7 +205,10 @@ Turborepo monorepo with 9 packages:
 | `agent_debate_create` | Create a turn-based debate session (returns debate ID) |
 | `agent_debate_turn` | Execute one provider's turn; supports `provider: "claude"` for Claude's independent participation |
 | `agent_debate_conclude` | End a debate and generate final transcript |
-| `agent_debate_moderate` | Run a fully automated debate — creates session, runs provider rounds, records specialist selection, applies it to Claude's host-backed turn when available, detects consensus, returns summary only |
+| `agent_debate_structured` | Start an approval-gated structured debate — individual reviews, optional alias clarification, rounds with vote aggregation, parks in `ready-for-approval` (no synthesis until approved) |
+| `agent_debate_approve` | Leader-approve a ready-for-approval structured debate; writes the synthesis document and closes the session |
+| `agent_debate_continue` | Run additional rounds on a ready-for-approval (or escalated) structured-debate session (3/5/10) |
+| `agent_debate_reject` | Reject a structured-debate session without writing synthesis |
 | `agent_debate_review` | Send a document to multiple providers for independent review |
 | `agent_cross_validate` | Cross-validate outputs (agent-tier validators only) |
 | `agent_changes_review` | Review file changes from an isolated task |

package/README.zh.md

@@ -164,7 +164,10 @@ Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/comma
 | `agent_debate_create` | 创建回合制辩论会话（返回 debate ID） |
 | `agent_debate_turn` | 执行某个提供方的一回合；支持 `provider: "claude"` 让 Claude 独立参与 |
 | `agent_debate_conclude` | 结束辩论并生成最终转录 |
-| `agent_debate_moderate` | 运行全自动辩论：创建会话、执行 provider 轮次、记录专家代理选择、检测共识，仅返回摘要 |
+| `agent_debate_structured` | 启动带审批闸门的结构化辩论：进行独立审查、可选别名整理、带投票聚合的多轮推进，合成在批准前不写入，会话停留在 `ready-for-approval` |
+| `agent_debate_approve` | 领导者批准 `ready-for-approval` 会话；写入合成文档并结束会话 |
+| `agent_debate_continue` | 对 `ready-for-approval`（或 `escalated`）会话追加轮次（3/5/10） |
+| `agent_debate_reject` | 拒绝结构化辩论会话，不写入合成 |
 | `agent_debate_review` | 将文档发送给多个提供方进行独立审查 |
 | `agent_cross_validate` | 对输出进行交叉验证（仅限 agent-tier validators） |
 | `agent_changes_review` | 审查隔离任务中的文件变更 |