agestra 4.4.1 → 4.4.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/agents/agestra-moderator.md +11 -9
- package/commands/review.md +12 -4
- package/dist/bundle.js +149 -148
- package/package.json +13 -13
- package/skills/review.md +8 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "agestra",
|
|
3
|
-
"version": "4.4.
|
|
3
|
+
"version": "4.4.2",
|
|
4
4
|
"description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, cross-validation, and GraphRAG memory",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"packageManager": "npm@11.11.0",
|
|
@@ -21,18 +21,18 @@
|
|
|
21
21
|
"hooks/",
|
|
22
22
|
"skills/"
|
|
23
23
|
],
|
|
24
|
-
"scripts": {
|
|
25
|
-
"sync:metadata": "node scripts/sync-metadata.mjs",
|
|
26
|
-
"prebuild": "npm run sync:metadata",
|
|
27
|
-
"build": "turbo build",
|
|
28
|
-
"test": "turbo test",
|
|
29
|
-
"dev": "turbo dev",
|
|
30
|
-
"lint": "turbo lint",
|
|
31
|
-
"clean": "turbo clean",
|
|
32
|
-
"prebundle": "npm run sync:metadata",
|
|
33
|
-
"bundle": "node scripts/bundle.mjs",
|
|
34
|
-
"prepublishOnly": "npm run build && npm run bundle"
|
|
35
|
-
},
|
|
24
|
+
"scripts": {
|
|
25
|
+
"sync:metadata": "node scripts/sync-metadata.mjs",
|
|
26
|
+
"prebuild": "npm run sync:metadata",
|
|
27
|
+
"build": "turbo build",
|
|
28
|
+
"test": "turbo test",
|
|
29
|
+
"dev": "turbo dev",
|
|
30
|
+
"lint": "turbo lint",
|
|
31
|
+
"clean": "turbo clean",
|
|
32
|
+
"prebundle": "npm run sync:metadata",
|
|
33
|
+
"bundle": "node scripts/bundle.mjs",
|
|
34
|
+
"prepublishOnly": "npm run build && npm run bundle"
|
|
35
|
+
},
|
|
36
36
|
"keywords": [
|
|
37
37
|
"claude-code-plugin",
|
|
38
38
|
"mcp",
|
package/skills/review.md
CHANGED
|
@@ -57,6 +57,14 @@ Only show options whose conditions are met. If no providers are available, run C
|
|
|
57
57
|
|
|
58
58
|
### Phase 4: Execute
|
|
59
59
|
|
|
60
|
+
#### Execution discipline for "각자 독립" and "끝장토론"
|
|
61
|
+
|
|
62
|
+
- 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).
|
|
63
|
+
- 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.
|
|
64
|
+
- 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.
|
|
65
|
+
- 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.
|
|
66
|
+
- 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.
|
|
67
|
+
|
|
60
68
|
#### If "Claude only":
|
|
61
69
|
Spawn the `agestra-reviewer` agent with the target and selected focus areas as context.
|
|
62
70
|
|