@desplega.ai/agent-swarm 1.2.1 → 1.9.0

package/cc-plugin/commands/start-worker.md

@@ -1,64 +0,0 @@
----
-description: Setup and start an Agent Swarm Worker
----
-
-# Agent Swarm Worker
-
-# Initial disclaimer
-
-If the `agent-swarm` MCP server is not configured or disabled, return immediately with the following message:
-
-```
-⚠️ The Agent Swarm MCP server is not configured or disabled. Please set up the MCP server to use the Agent Swarm features.
-
-I can not serve you, my lord, if the MCP server is not properly configured. Go ask your admin to set it up properly. GTFO.
-```
-
-## Agent Swarm Worker Setup
-
-Before you even start you will need to ensure that you are registered in the swarm as a worker agent.
-
-To do so, use the `agent-swarm` MCP server and call the `join-swarm` tool providing a name. 
-
-For the name, check if the user specified one, if not, proceed to use one that fits based on your context (e.g., project name, repo name, etc.).
-
-Here are some examples names that are OK:
-
-- "Worker Bee 001"
-- "Task Executor Alpha"
-- "Task Executor Beta" (if alpha is taken lol)
-- "Project Assistant"
-- "Bullshit Job Worker #1337"
-- "AI Minion"
-- "Code Monkey"
-- "agent #14"
-
-You get the idea. Be creative, but also clear that you are a worker agent.
-
-## Agent Swarm Worker Start
-
-The first thing you need to do, is use the `get-tasks` tool with `mineOnly` set to true, to check what tasks you might have in progress or assigned to you.
-
-If there's a task that is in progress, you should resume working on it!
-
-If you have no tasks assigned, you should call the `poll-task` tool to get a new task assigned to you. This will poll for a while and return either with:
-
-1. A new task assigned to you
-2. A message indicating there's no tasks available right now
-
-If 2, start polling immediately FOREVER. Only stop if you get interrupted by the user, if not, just keep polling.
-
-### You got a task assigned!
-
-Once you get a task assigned you should immediately start working on it. To do so, you should:
-
-1. Call `store-progress` tool to mark the task as "in-progress" with a progress set to something like "Starting work on the task XXX, blah blah"
-2. Start working on the task, providing updates as needed by calling `store-progress` tool, use the `progress` field to indicate what you are doing.
-
-If you get interrupted by the user, that is fine, it might happen. Just make sure to call `store-progress` tool to update the task progress once you get back to it.
-
-Once you are done, or in a real dead-end, you should call `store-progress` tool to mark the task as "complete" or "failed" as needed.
-
-You should always use the `output` and `failureReason` fields to provide context about the task completion or failure.
-
-Once you are done (either ok or not), you should go back to polling for new tasks.

package/docker-compose.worker.yml

@@ -1,35 +0,0 @@
-# Docker Compose for Agent Swarm Worker
-#
-# Usage:
-#   docker-compose -f docker-compose.worker.yml up --build
-#
-# Required environment variables (in .env.docker or passed directly):
-#   - CLAUDE_CODE_OAUTH_TOKEN: OAuth token for Claude CLI
-#   - API_KEY: API key for MCP server authentication
-#
-# Optional environment variables:
-#   - AGENT_ID: UUID for agent identification (assigned on join if not set)
-#   - MCP_BASE_URL: MCP server URL (default: http://host.docker.internal:3013)
-#   - SESSION_ID: Folder name for logs (auto-generated if not provided)
-#   - WORKER_YOLO: If "true", continue on errors (default: false)
-
-services:
-  worker:
-    build:
-      context: .
-      dockerfile: Dockerfile.worker
-    environment:
-      - CLAUDE_CODE_OAUTH_TOKEN=${CLAUDE_CODE_OAUTH_TOKEN}
-      - API_KEY=${API_KEY}
-      - AGENT_ID=${AGENT_ID:-}
-      # Use host.docker.internal to reach host's localhost on Mac/Windows
-      # On Linux, use --add-host=host.docker.internal:host-gateway or --network host
-      - MCP_BASE_URL=${MCP_BASE_URL:-http://host.docker.internal:3013}
-      - SESSION_ID=${SESSION_ID:-}
-      - WORKER_YOLO=${WORKER_YOLO:-false}
-    volumes:
-      - ./logs:/logs
-      # Optional: mount a workspace directory for persistent work
-      # - ./workspace:/workspace
-    restart: unless-stopped
-    # No port mappings needed - worker only makes outbound connections

package/example-req-meta.json

@@ -1,24 +0,0 @@
-{
-  "meta": {
-    "signal": {},
-    "sessionId": "942c8196-66ad-4c1f-b31e-7331ce7f4bb9",
-    "_meta": {
-      "progressToken": 3
-    },
-    "requestId": 3,
-    "requestInfo": {
-      "headers": {
-        "accept": "application/json, text/event-stream",
-        "accept-encoding": "gzip, deflate, br",
-        "authorization": "Bearer 123123",
-        "connection": "keep-alive",
-        "content-length": "119",
-        "content-type": "application/json",
-        "host": "localhost:3013",
-        "mcp-protocol-version": "2025-11-25",
-        "mcp-session-id": "942c8196-66ad-4c1f-b31e-7331ce7f4bb9",
-        "user-agent": "node-fetch"
-      }
-    }
-  }
-}