79 lines
3.1 KiB
YAML
79 lines
3.1 KiB
YAML
# 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: 2
|
|
reasoning_effort: high
|
|
delegation:
|
|
max_concurrent_children: 2
|
|
max_spawn_depth: 1
|
|
web:
|
|
backend: ddgs
|
|
search_backend: ddgs
|
|
extract_backend: public-extract
|
|
model_catalog:
|
|
enabled: true
|
|
ttl_hours: 1
|
|
platform_toolsets:
|
|
cli: [clarify, delegation, file, memory, python_sandbox, session_search, skills, todo, web]
|
|
api_server: [clarify, delegation, file, memory, python_sandbox, session_search, skills, todo, 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,
|
|
extract the most relevant primary pages, and cite the sources used.
|
|
|
|
Complete complex work instead of stopping after a preflight. For involved
|
|
research or analysis, make a short internal plan, delegate independent
|
|
research when that improves coverage, use the isolated Python sandbox for
|
|
statistics/probability/simulation, check the result, and synthesize one
|
|
coherent answer. State assumptions and uncertainty where exact inputs are
|
|
unavailable. Never tell the user to enable a tool that is already present.
|
|
|
|
This is a personal sandbox. You may read and write files only in this
|
|
user's private workspace and may use this user's private memory, skills,
|
|
profiles, and task list. Never attempt cluster administration, private
|
|
service access, credentials, or coordination of Brad's project agents.
|
|
Python may run only through the credential-free sandbox tool. 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 the private workspace,
|
|
memory, skills, profiles, task list, session search, public web tools, and
|
|
the separate per-tenant Python sandbox. Use delegation selectively for
|
|
independent research or verification, then present a single final answer.
|
|
Do not claim access to Kubernetes, Vault, Gitea, Brad's projects, other
|
|
users, the agent coordinator, or automated triage.
|