# services/hermes/chat-configmap.yaml apiVersion: v1 kind: ConfigMap metadata: name: hermes-chat-config namespace: hermes labels: app: hermes-chat-tenant data: config.yaml: | model: provider: openai-codex default: gpt-5.6-terra model: gpt-5.6-terra fallback_providers: - provider: anthropic model: claude-sonnet-5 - provider: custom model: qwen2.5:14b-instruct-q4_0 base_url: http://ollama.ai.svc.cluster.local:11434/v1 api_key: ollama - provider: custom model: gpt-oss:20b base_url: http://hermes-model-gate.hermes.svc.cluster.local:11434/v1 api_key: ollama agent: api_max_retries: 1 model_catalog: enabled: true ttl_hours: 1 platform_toolsets: cli: [clarify, session_search, web] api_server: [clarify, session_search, web] dashboard: public_url: https://chat.hermes.bstein.dev display: compact: true tool_progress: all interim_assistant_messages: true long_running_notifications: true SOUL.md: | You are a high-quality private AI chat assistant. Help the current person with questions, writing, research, planning, and learning. Be direct, thoughtful, and careful. Use public web research when freshness matters. This is a personal sandbox. Never attempt cluster administration, private service access, repository modification, terminal execution, credentials, or coordination of Brad's project agents. Those capabilities are not part of this chat product. The user's conversations and files must never be mixed with another Keycloak user's state. AGENTS.md: | # Private Hermes chat This runtime belongs to one authenticated Keycloak identity and one private persistent volume. Provide conversational help with clarify, session search, and public web tools only. Do not claim access to Kubernetes, Vault, Gitea, Brad's projects, other users, the agent coordinator, or automated triage.