fix(minimax-mem0): convert to Agent Plugins 1.0 format (plugin.json + mcp.json at root)

The runtime imports validate against the open Agent Plugins 1.0 spec
(agent-plugins.org), not the Feishu submission guide's .minimax-plugin/ layout.
Discovered via the in-app import (GitHub Plugin cannot be imported).

integrations/minimax-mem0/.minimax-plugin/plugin.json

@@ -1,18 +0,0 @@
-{
-  "schemaVersion": 1,
-  "name": "mem0",
-  "displayName": "Mem0 Memory",
-  "version": "0.1.0",
-  "description": "Persistent long-term memory for your agent: remember preferences, decisions, and project context across sessions, and recall them on demand.",
-  "author": "Mem0",
-  "icon": "icon.png",
-  "category": "Productivity",
-  "exampleQueries": [
-    "Remember that I prefer TypeScript and pnpm",
-    "What do you remember about my project?",
-    "Update what you know about my deployment setup"
-  ],
-  "apps": [],
-  "mcpServers": ["mem0.mcp.json"],
-  "skills": ["skills/memory/SKILL.md"]
-}

integrations/minimax-mem0/README.md

@@ -8,12 +8,13 @@ It gives a MiniMax agent persistent long-term memory: it remembers the user's pr
 
 This is a declarative MiniMax plugin (no build step). It follows the MiniMax plugin spec:
 
+Built to the [Agent Plugins 1.0](https://agent-plugins.org/specification) standard, which the MiniMax runtime imports and validates against.
+
 ```
 minimax-mem0/
-  .minimax-plugin/
-    plugin.json          # manifest (schemaVersion 1)
-  icon.png               # 180x180 square Mem0 icon
-  mem0.mcp.json          # remote MCP: https://mcp.mem0.ai/mcp/ (streamable-http)
+  plugin.json            # manifest (Agent Plugins 1.0, at plugin root)
+  mcp.json               # remote MCP: https://mcp.mem0.ai/mcp/ (auto-discovered at root)
+  icon.png               # square Mem0 icon
   skills/
     memory/
       SKILL.md           # when to recall / save / update memory
@@ -21,7 +22,7 @@ minimax-mem0/
 
 Two capabilities:
 
-- **MCP** (`mem0.mcp.json`) points at Mem0's hosted MCP server (`https://mcp.mem0.ai/mcp/`), which exposes the memory tools (`add_memory`, `search_memories`, `update_memory`, `delete_memory`, and more). No secrets are stored in the package.
+- **MCP** (`mcp.json`) points at Mem0's hosted MCP server (`https://mcp.mem0.ai/mcp/`), which exposes the memory tools (`add_memory`, `search_memories`, `update_memory`, `delete_memory`, and more). No secrets are stored in the package.
 - **Skill** (`skills/memory/SKILL.md`) tells the agent when to search, save, update, and delete memory so recall happens automatically.
 
 ## Authentication

integrations/minimax-mem0/mcp.json

@@ -0,0 +1,9 @@
+{
+  "$schema": "https://agent-plugins.org/schemas/1.0.0/mcp.schema.json",
+  "mcpServers": {
+    "mem0": {
+      "type": "streamable-http",
+      "url": "https://mcp.mem0.ai/mcp/"
+    }
+  }
+}

integrations/minimax-mem0/mem0.mcp.json

@@ -1,11 +0,0 @@
-{
-  "schemaVersion": 1,
-  "mcpServers": {
-    "mem0": {
-      "type": "streamable-http",
-      "url": "https://mcp.mem0.ai/mcp/",
-      "description": "Mem0 long-term memory: add, search, update, and delete memories so the agent remembers context across sessions.",
-      "timeout": 30000
-    }
-  }
-}

integrations/minimax-mem0/plugin.json

@@ -0,0 +1,11 @@
+{
+  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
+  "name": "mem0",
+  "version": "0.1.0",
+  "description": "Persistent long-term memory for your agent: remember preferences, decisions, and project context across sessions, and recall them on demand.",
+  "author": { "name": "Mem0", "email": "support@mem0.ai", "url": "https://mem0.ai" },
+  "homepage": "https://mem0.ai",
+  "repository": "https://github.com/mem0ai/mem0",
+  "license": "Apache-2.0",
+  "keywords": ["memory", "long-term-memory", "personalization", "mcp"]
+}