agestra 4.5.6 → 4.5.7

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": "4.5.6",
+      "version": "4.5.7",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.5.6",
+  "version": "4.5.7",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
   "mcpServers": {
     "agestra": {

package/commands/review.md

@@ -67,16 +67,18 @@ Only show options whose conditions are met. If no providers are available, skip
 
 - Prefer Agestra MCP tools for external providers (`ai_chat`, `ai_analyze_files`, `agent_debate_*`, `workspace_*`, `cli_job_submit` when a direct provider retry is needed).
 - Do NOT launch raw Bash retries such as `codex exec ...` or `gemini ...` yourself, and do NOT invent provider-specific flags. If a retry is required, use `cli_job_submit` with the provider's default mapping unless you have just verified the current CLI help output in this environment.
+- Exclude `ollama` from review workflows even if it is available. For repository/code reviews, use only review-capable external providers such as `gemini`, `codex`, and registered Claude-backed reviewers.
 - Treat the Claude reviewer agent as asynchronous work that may legitimately take several minutes. Poll about once per minute; an empty or slowly growing output file is not a failure by itself.
 - Do NOT stop or replace the Claude reviewer with a duplicate main-thread review unless there is an explicit error, the user asks to cancel, or there has been no visible progress for at least 8 minutes. For large review scopes, allow up to 15 minutes before declaring the reviewer stalled.
 - If a background reviewer is still running, tell the user you are waiting and continue the orchestration. Do not short-circuit the workflow just because another provider finished earlier.
+- For "끝장토론", do NOT use `agent_debate_moderate` as the primary review path. Use the turn-based flow (`agent_debate_create` + iterative `agent_debate_review` / `agent_debate_turn` + `agent_debate_conclude`) so long-running review rounds do not get cut off by host tool-call time limits.
 
 ### If "Claude only":
 Spawn the `agestra-reviewer` agent with the target and selected focus areas as context.
 
 ### If "각자 독립":
 
-**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 사용 가능한 외부 AI (gemini, codex, ollama 등)
+**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 리뷰용 외부 AI (`gemini`, `codex`, 등록된 Claude-backed reviewer 등; `ollama` 제외)
 
 1. In parallel:
    - Spawn the `agestra-reviewer` agent for Claude's independent analysis.
@@ -111,25 +113,29 @@ Spawn the `agestra-reviewer` agent with the target and selected focus areas as c
 
 ### If "끝장토론":
 
-**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 사용 가능한 외부 AI (gemini, codex, ollama 등)
-
-1. Execute "각자 독립" steps 1-3 above (independent work + initial aggregation).
-   - The moderator's integrated document becomes the starting document.
-
-2. Document review rounds (no max — until all agree):
-   a. Moderator sends the current document to each AI for review:
-      - Claude: spawn `agestra-reviewer` → analyze document → write section-by-section feedback
-      - Other providers: `agent_debate_turn` with the document as prompt, requesting agree/disagree per section
-   b. Moderator collects all feedback.
-   c. Classify: agree/disagree per section per provider.
-   d. Revise document incorporating disagreement feedback.
-   e. If all providers agree on all sections → consensus reached.
-   f. If not → next round with revised document.
-   g. **Every 10 rounds:** Ask the user via AskUserQuestion whether to continue or stop with current state.
-
-3. Present the final document:
-   - Consensus sections: marked as agreed
-   - Disputed sections: show split positions with each provider's rationale
+**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 리뷰용 외부 AI (`gemini`, `codex`, 등록된 Claude-backed reviewer 등; `ollama` 제외)
+
+1. Execute "각자 독립" steps 1-3 above (independent work + initial aggregation).
+   - The moderator's integrated document becomes the starting document.
+
+2. Start a turn-based debate session with `agent_debate_create`.
+   - Use the integrated document's title/topic as the debate topic.
+   - Reuse the same reviewer set from step 1, excluding `ollama`.
+
+3. Document review rounds (no max — until all agree):
+   a. Moderator sends the current document to Claude reviewer asynchronously.
+   b. Moderator sends the same current document to non-Claude providers with `agent_debate_review`.
+   c. Moderator collects all feedback and updates the working document.
+   d. If a provider needs a follow-up reply to another provider's point, add a targeted `agent_debate_turn` in the same debate session rather than restarting the workflow.
+   e. If all providers agree on all sections → consensus reached.
+   f. If not → next round with the revised document.
+   g. **Every 10 rounds:** Ask the user via AskUserQuestion whether to continue or stop with current state.
+
+4. When consensus is reached, record the moderator's final synthesis with `agent_debate_conclude`.
+
+5. Present the final document:
+   - Consensus sections: marked as agreed
+   - Disputed sections: show split positions with each provider's rationale
 
 ### If "Other":
 Follow the user's specified approach.