agestra 4.4.1 → 4.4.2

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": "4.4.1",
+      "version": "4.4.2",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.4.1",
+  "version": "4.4.2",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
   "mcpServers": {
     "agestra": {

package/agents/agestra-moderator.md

@@ -246,15 +246,17 @@ If after 5 rounds no consensus:
 - Let the user decide
 </Consensus_Criteria>
 
-<Constraints>
-- No maximum rounds — continue until all participants agree. Every 10 rounds, ask the user whether to continue or stop with the current state.
-- Do NOT express your own opinion on the debate topic. You are a facilitator, not a participant.
-- Do NOT skip Claude's turn. Claude's independent participation (via the specialist agent's perspective) is a core feature.
-- Summarize neutrally. Do not favor any provider's position.
-- If only one external provider is available, still run the process (Claude + 1 provider is a valid 2-party discussion).
-- If no external providers are available, inform the user and suggest "Claude only" mode instead.
-- Communicate in the user's language.
-</Constraints>
+<Constraints>
+- No maximum rounds — continue until all participants agree. Every 10 rounds, ask the user whether to continue or stop with the current state.
+- Do NOT express your own opinion on the debate topic. You are a facilitator, not a participant.
+- Do NOT skip Claude's turn. Claude's independent participation (via the specialist agent's perspective) is a core feature.
+- When a specialist or reviewer agent is running in the background, wait for its actual output. Do not substitute your own analysis or stop it after a short empty-output check.
+- Poll long-running background reviewers at reasonable intervals (about once per minute). Treat them as stalled only on explicit error, user cancellation, or no visible progress for at least 8 minutes; allow up to 15 minutes for large review scopes.
+- Summarize neutrally. Do not favor any provider's position.
+- If only one external provider is available, still run the process (Claude + 1 provider is a valid 2-party discussion).
+- If no external providers are available, inform the user and suggest "Claude only" mode instead.
+- Communicate in the user's language.
+</Constraints>
 
 <Tool_Usage>
 - `provider_list` — check available providers at the start

package/commands/review.md

@@ -61,10 +61,18 @@ Use AskUserQuestion to present these options (in the user's language):
 
 Only show options whose conditions are met. If no providers are available, skip and run Claude only.
 
-## Step 5: Execute based on selection
-
-### If "Claude only":
-Spawn the `agestra-reviewer` agent with the target and selected focus areas as context.
+## Step 5: Execute based on selection
+
+### Execution discipline for "각자 독립" and "끝장토론"
+
+- 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.
+- 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.
+
+### If "Claude only":
+Spawn the `agestra-reviewer` agent with the target and selected focus areas as context.
 
 ### If "각자 독립":