Skip to content

claude-code.md

Latest commit

 

History

History
50 lines (35 loc) · 1.54 KB

claude-code.md

File metadata and controls

50 lines (35 loc) · 1.54 KB

Claude Code

Claude Code uses the @agentclientprotocol/claude-agent-acp adapter for ACP support.

Docker Image

docker build -f Dockerfile.claude -t openab-claude:latest .

The image installs @agentclientprotocol/claude-agent-acp and @anthropic-ai/claude-code globally via npm.

Helm Install

helm install openab openab/openab \
  --set agents.kiro.enabled=false \
  --set agents.claude.discord.botToken="$DISCORD_BOT_TOKEN" \
  --set-string 'agents.claude.discord.allowedChannels[0]=YOUR_CHANNEL_ID' \
  --set agents.claude.image=ghcr.io/openabdev/openab-claude:latest \
  --set agents.claude.command=claude-agent-acp \
  --set agents.claude.workingDir=/home/node

Set agents.kiro.enabled=false to disable the default Kiro agent.

Manual config.toml

[agent]
command = "claude-agent-acp"
args = []
working_dir = "/home/node"

Authentication

Sign in interactively using the OAuth device flow. Credentials are stored on disk (persisted via PVC across pod restarts):

kubectl exec -it deployment/openab-claude -- claude auth login

After authenticating, restart the pod so the bot process loads the new credentials:

kubectl rollout restart deployment/openab-claude

Note: claude setup-token is a different command — it generates a long-lived token for CI/scripts and prints it without saving locally. For container-based deployments, claude auth login is the correct approach as it persists credentials to the filesystem.