agestra 4.7.0 → 4.8.0

package/skills/review.md

@@ -45,76 +45,55 @@ Ask what to focus on (multiSelect):
 
 Call `environment_check` to determine available providers.
 
-Present mode selection (in the user's language):
+- If **no providers are available**: run the `agestra-reviewer` agent directly (Claude only) with the target and selected focus areas as context. Skip to Phase 5.
+- If **1+ providers are available**: proceed to 끝장토론 execution below.
 
-| Option | Condition | Description |
-|--------|-----------|-------------|
-| **Claude only** | Always | 플러그인 전문 에이전트가 단독 리뷰 |
-| **각자 독립** | 1+ provider available | 에이전트 팀(moderator + reviewer + 외부 AI)이 각자 독립 리뷰 후 취합 문서 작성 |
-| **끝장토론** | 1+ provider available | 각자 독립 리뷰 후 취합 문서를 돌아가며 분석/피드백, 모두 동의할 때까지 |
+### Phase 4: Execute 끝장토론
 
-Only show options whose conditions are met. If no providers are available, run Claude only.
-
-### Phase 4: Execute
-
-#### Execution discipline for "각자 독립" and "끝장토론"
+#### Execution discipline
 
 - 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":
-
-**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 사용 가능한 외부 AI (gemini, codex, ollama 등)
-
-1. In parallel:
-   - Spawn the `agestra-reviewer` agent for Claude's independent analysis.
-     After the agent completes, save Claude's result as a document via `workspace_create_document`:
-     - **title:** `Code Review — claude/reviewer`
-     - **metadata:** `{ "Provider": "claude/reviewer", "Task": "{review target}", "Focus": "{selected focus areas}", "Mode": "Independent" }`
-     - **content:** The reviewer agent's full output.
-   - For each available provider, call `ai_chat` with `save_as_document`:
-     - **save_as_document.title:** `Code Review — {provider}`
-     - **save_as_document.metadata:** `{ "Task": "{review target}", "Focus": "{selected focus areas}", "Mode": "Independent" }`
-     - **prompt:** Review the following code. Focus on: [selected focus areas]. For each finding, provide severity (CRITICAL/HIGH/MEDIUM/LOW), file:line location, and evidence. Target: [the review target]
-
-2. Collect all document IDs.
-
-3. Spawn the `agestra-moderator` agent in **Independent Aggregation** mode:
-   - Pass the document ID list.
-   - Moderator reads each document, classifies consensus/unique/disputed findings.
-   - Moderator creates an aggregated document via `workspace_create_document`.
-
-4. Present summary report to the user:
-   - Key consensus findings (1-3 lines).
-   - Notable unique findings (if any).
-   - Disputed points (if any).
-   - Individual + aggregated document IDs.
-
-#### 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 → 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 whether to continue or stop with current state.
-
-3. Present the final document:
+- Do NOT launch raw Bash retries such as `codex exec ...` or `gemini ...` yourself, and do NOT invent provider-specific flags.
+- Exclude `ollama` from review workflows. Use only review-capable external providers (gemini, codex, registered Claude-backed reviewers).
+- Treat the Claude reviewer agent as asynchronous work that may take several minutes. Poll about once per minute.
+- Do NOT stop or replace the Claude reviewer unless there is an explicit error, user cancellation, or no visible progress for 8+ minutes.
+- Do NOT use `agent_debate_moderate` as the primary review path. Use the turn-based flow (`agent_debate_create` + `agent_debate_turn` + `agent_debate_conclude`).
+
+**팀 구성:** `agestra-moderator` (리더) + `agestra-reviewer` (Claude) + 리뷰용 외부 AI (gemini, codex 등; ollama 제외)
+
+1. Independent work + initial aggregation:
+
+   a. In parallel:
+      - Spawn the `agestra-reviewer` agent for Claude's independent analysis.
+        After the agent completes, save Claude's result as a document via `workspace_create_document`:
+        - **title:** `Code Review — claude/reviewer`
+        - **metadata:** `{ "Provider": "claude/reviewer", "Task": "{review target}", "Focus": "{selected focus areas}", "Mode": "Independent" }`
+        - **content:** The reviewer agent's full output.
+      - For each available provider, call `ai_chat` with `save_as_document`:
+        - **save_as_document.title:** `Code Review — {provider}`
+        - **save_as_document.metadata:** `{ "Task": "{review target}", "Focus": "{selected focus areas}", "Mode": "Independent" }`
+        - **prompt:** Review the following code. Focus on: [selected focus areas]. For each finding, provide severity (CRITICAL/HIGH/MEDIUM/LOW), file:line location, and evidence. Target: [the review target]
+
+   b. Collect all document IDs.
+
+   c. Spawn the `agestra-moderator` agent in **Independent Aggregation** mode:
+      - Pass the document ID list.
+      - Moderator reads each document, classifies consensus/unique/disputed findings.
+      - Moderator creates an aggregated document via `workspace_create_document`.
+      - The moderator's integrated document becomes the starting document.
+
+2. Start a turn-based debate session with `agent_debate_create`.
+
+3. Document review rounds (no max — until all agree):
+   a. Moderator sends the current document to each AI for review.
+   b. Moderator collects all feedback and updates the working document.
+   c. If all providers agree on all sections → consensus reached.
+   d. If not → next round with the revised document.
+   e. **Every 10 rounds:** Ask the user whether to continue or stop with current state.
+
+4. When consensus is reached, record the 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
 

package/skills/setup.md

@@ -0,0 +1,98 @@
+---
+name: setup
+description: >
+  Agestra 초기 설정 및 AI 선택. 사용할 AI를 선택하고 providers.config.json을 생성합니다.
+  처음 사용할 때, AI를 바꾸고 싶을 때, 설정을 변경하고 싶을 때 사용합니다.
+  트리거: "agestra setup", "AI 설정", "provider 설정", "어떤 AI 쓸지",
+  "AI 바꾸고 싶어", "초기 설정", "provider 변경", "gemini 끄고 싶어",
+  "codex만 쓰고 싶어", "설정 변경", "setup", "세팅"
+---
+
+## Setup Flow
+
+### Step 1: Detect installed CLIs
+
+Call `environment_check` to detect which AI CLIs are installed on the system.
+
+### Step 2: Ask user which AIs to use
+
+Based on detection results, present ONLY the installed/available AIs as choices.
+Use the user's language for the question.
+
+**Korean example:**
+```
+사용할 AI를 선택하세요:
+  ☑ Codex CLI (설치됨)
+  ☑ Claude CLI (설치됨)
+  ☐ Gemini CLI (설치됨)
+  ☐ Ollama (localhost:11434)
+```
+
+**Also ask the session preference:**
+```
+세션 시작 시 매번 사용할 AI를 선택하시겠습니까?
+  ○ 예 (매번 선택)
+  ○ 아니오 (이번 설정을 계속 사용)
+```
+
+### Step 3: Generate providers.config.json
+
+Based on user selection, generate the config file directly:
+
+```json
+{
+  "defaultProvider": "<first-selected-provider-id>",
+  "selectionPolicy": "ask-each-session" | "fixed",
+  "providers": [
+    {
+      "id": "codex",
+      "type": "codex-cli",
+      "enabled": true,
+      "executionPolicy": "workspace-write",
+      "config": { "timeout": 120000 }
+    },
+    {
+      "id": "gemini",
+      "type": "gemini-cli",
+      "enabled": false,
+      "executionPolicy": "workspace-write",
+      "config": { "timeout": 120000 }
+    }
+  ]
+}
+```
+
+**Rules:**
+- Only selected providers get `enabled: true`
+- Unselected but installed providers get `enabled: false`
+- Not installed providers are omitted entirely
+- `selectionPolicy`: `"ask-each-session"` if user chose "매번 선택", `"fixed"` otherwise
+- Write to `{workspace}/providers.config.json`
+
+### Step 4: Confirm and proceed
+
+After config is saved, confirm to user:
+
+```
+설정 완료! Codex, Claude CLI가 활성화되었습니다.
+끝장토론(debate)에서 이 AI들이 사용됩니다.
+설정을 변경하려면 /agestra setup을 다시 실행하세요.
+```
+
+## Session Start Behavior
+
+When `selectionPolicy` is `"ask-each-session"`:
+- At session start, present the AI selection question again
+- User can quickly confirm previous selection or change it
+- Update config accordingly
+
+When `selectionPolicy` is `"fixed"`:
+- Use existing config without asking
+- User can still run `/agestra setup` to change
+
+## Integration with Debate
+
+When user triggers review/idea/design (via hook or command):
+- Skip the "Claude only / 독립 / 끝장토론" choice
+- Go directly to 끝장토론 (debate) mode using the enabled providers
+- If only 1 provider is enabled, inform user that debate needs 2+ participants and offer to add Claude as participant

package/skills/trace.md

@@ -4,7 +4,8 @@ description: >
   Use when the user wants to see agent execution flow, debug agent interactions,
   view timeline of recent operations, or understand what happened during a
   multi-AI session. Triggers on: "trace", "what happened", "show flow",
-  "agent timeline", "execution history", "bottleneck", "performance".
+  "agent timeline", "execution history", "bottleneck", "performance",
+  "뭐 했어", "기록 보여줘", "실행 기록", "타임라인".
 ---
 
 ## Purpose
@@ -32,7 +33,7 @@ Aggregate statistics for a session or time range:
 
 1. Call `trace_summary` to get aggregate data
 2. Present:
-   - Total events by type (debate turns, dispatches, comparisons, memory ops)
+   - Total events by type (debate turns, dispatches, comparisons)
    - Provider usage breakdown (which providers were called, how often)
    - Success/failure rates per provider
    - Average response times