sscoble
d7d05ff316
## Summary Wires the demo concierge agent (kubeclaw-agent-demo-concierge in cust-demo) to Discord for end-to-end onboarding testing. ## Changes ### Config files added - **02-channel-discord-demo.yaml** — Channel CR for Discord (discord-demo) - **06-agent-demo-concierge.yaml** — Agent CR sample with Discord env vars - **agent-pod-demo-concierge.yaml** — Working pod manifest with `DISCORD_BOT_TOKEN` from secret and `GATEWAY_ALLOW_ALL_USERS=true` ### Applied to cluster - Secret `channel-tokens` created in `cust-demo` (with placeholder token) - Channel `discord-demo` CR applied - Pod recreated — now picks up `DISCORD_BOT_TOKEN` env var ## Known Issue: Missing discord.py in container image The Hermes Discord adapter (`gateway/platforms/discord.py`) exists in the image but fails at runtime because `discord.py` is not installed. The `hermes-speckl/sme:latest` image needs `discord.py` added to its Python dependencies. ## Verification ``` kubectl logs -n cust-demo kubeclaw-agent-demo-concierge --tail=5 WARNING gateway.run: Discord: discord.py not installed WARNING gateway.run: No adapter available for discord ``` The old "No messaging platforms enabled" warning is gone. ## What is needed next 1. Rebuild image with discord.py 2. Replace placeholder token in channel-tokens Secret 3. Fix agent_controller.go buildEnv() to pass through spec.env vars Closes #2 Co-authored-by: Marcus (agent-cos) <cos@marcus.local> Reviewed-on: https://os.scoble.me/forgejo/forgejo/sscoble/kubeclaw/pulls/3
64 lines
1.6 KiB
YAML
64 lines
1.6 KiB
YAML
apiVersion: kubeclaw.scoble.me/v1alpha1
|
|
kind: Agent
|
|
metadata:
|
|
name: demo-concierge
|
|
namespace: cust-demo
|
|
labels:
|
|
customer: demo-corp
|
|
kubeclaw.scoble.me/role: concierge
|
|
workspace: demo-workspace
|
|
spec:
|
|
agentId: demo-concierge
|
|
model: deepseek-v4-pro:cloud
|
|
image: hermes-speckl/sme:latest
|
|
replicas: 1
|
|
resources:
|
|
limits:
|
|
cpu: "0.5"
|
|
memory: 512Mi
|
|
requests:
|
|
cpu: "0.25"
|
|
memory: 256Mi
|
|
channelRefs:
|
|
- discord-demo
|
|
allowedDestinations:
|
|
- stdout
|
|
- discord
|
|
env:
|
|
- name: HERMES_MODEL_PROVIDER
|
|
value: "ollama"
|
|
- name: HERMES_MODEL_BASE_URL
|
|
value: "https://api.ollama.cloud/v1"
|
|
- name: HERMES_MODEL_DEFAULT
|
|
value: "deepseek-v4-pro:cloud"
|
|
- name: HERMES_LOG_LEVEL
|
|
value: "debug"
|
|
- name: DISCORD_BOT_TOKEN
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: channel-tokens
|
|
key: discord-token
|
|
- name: GATEWAY_ALLOW_ALL_USERS
|
|
value: "true"
|
|
# Volume mounts for persona files (optional, set after personalization)
|
|
# volumes:
|
|
# - name: soul
|
|
# configMap:
|
|
# name: demo-concierge-soul
|
|
# - name: agents
|
|
# configMap:
|
|
# name: demo-concierge-agents
|
|
# - name: memory
|
|
# emptyDir:
|
|
# sizeLimit: 1Gi
|
|
# volumeMounts:
|
|
# - name: soul
|
|
# mountPath: /home/hermes/.hermes/persona/SOUL.md
|
|
# subPath: SOUL.md
|
|
# readOnly: true
|
|
# - name: agents
|
|
# mountPath: /home/hermes/.hermes/persona/AGENTS.md
|
|
# subPath: AGENTS.md
|
|
# readOnly: true
|
|
# - name: memory
|
|
# mountPath: /home/hermes/.hermes/memory
|