model:
  default: claude-opus-4-6
  provider: anthropic
toolsets:
- all
agent:
  max_turns: 30
  reasoning_effort: medium
  verbose: false
terminal:
  backend: local
  cwd: .
  timeout: 180
  docker_image: nikolaik/python-nodejs:python3.11-nodejs20
  docker_forward_env: []
  singularity_image: docker://nikolaik/python-nodejs:python3.11-nodejs20
  modal_image: nikolaik/python-nodejs:python3.11-nodejs20
  daytona_image: nikolaik/python-nodejs:python3.11-nodejs20
  container_cpu: 1
  container_memory: 5120
  container_disk: 51200
  container_persistent: true
  docker_volumes: []
  docker_mount_cwd_to_workspace: false
  persistent_shell: true
browser:
  inactivity_timeout: 120
  record_sessions: false
checkpoints:
  enabled: true
  max_snapshots: 50
compression:
  enabled: true
  threshold: 0.5
  summary_model: qwen3:30b
  summary_provider: custom
  summary_base_url: http://localhost:11434/v1
smart_model_routing:
  enabled: true
  max_simple_chars: 200
  max_simple_words: 35
  cheap_model:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
auxiliary:
  vision:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
    timeout: 30
  web_extract:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
  compression:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
  session_search:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
  skills_hub:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
  approval:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
  mcp:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
  flush_memories:
    provider: custom
    model: qwen3:30b
    base_url: http://localhost:11434/v1
    api_key: ollama
display:
  compact: false
  personality: ''
  resume_display: full
  bell_on_complete: false
  show_reasoning: false
  streaming: false
  show_cost: false
  skin: timmy
  tool_progress: all
privacy:
  redact_pii: false
tts:
  provider: edge
  edge:
    voice: en-US-AriaNeural
  elevenlabs:
    voice_id: pNInz6obpgDQGcFmaJgB
    model_id: eleven_multilingual_v2
  openai:
    model: gpt-4o-mini-tts
    voice: alloy
  neutts:
    ref_audio: ''
    ref_text: ''
    model: neuphonic/neutts-air-q4-gguf
    device: cpu
stt:
  enabled: true
  provider: local
  local:
    model: base
  openai:
    model: whisper-1
voice:
  record_key: ctrl+b
  max_recording_seconds: 120
  auto_tts: false
  silence_threshold: 200
  silence_duration: 3.0
human_delay:
  mode: 'off'
  min_ms: 800
  max_ms: 2500
memory:
  memory_enabled: true
  user_profile_enabled: true
  memory_char_limit: 2200
  user_char_limit: 1375
  nudge_interval: 10
  flush_min_turns: 6
delegation:
  model: ''
  provider: ''
  base_url: ''
  api_key: ''
prefill_messages_file: ''
honcho: {}
timezone: ''
discord:
  require_mention: true
  free_response_channels: ''
  auto_thread: true
whatsapp: {}
approvals:
  mode: manual
command_allowlist: []
quick_commands: {}
personalities: {}
security:
  redact_secrets: true
  tirith_enabled: true
  tirith_path: tirith
  tirith_timeout: 5
  tirith_fail_open: true
  website_blocklist:
    enabled: false
    domains: []
    shared_files: []
_config_version: 10
platforms:
  api_server:
    enabled: true
    extra:
      host: 0.0.0.0
      port: 8642
session_reset:
  mode: none
  idle_minutes: 0
custom_providers:
- name: Local Ollama
  base_url: http://localhost:11434/v1
  api_key: ollama
  model: glm-4.7-flash:latest
system_prompt_suffix: "You are Timmy. Your soul is defined in SOUL.md \u2014 read\
  \ it, live it.\nYou run locally on your owner's machine via Ollama. You never phone\
  \ home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
  When you don't know something, say so. Refusal over fabrication.\nSovereignty and\
  \ service always.\n"
skills:
  creation_nudge_interval: 15
DISCORD_HOME_CHANNEL: '1476292315814297772'
providers:
  ollama:
    base_url: http://localhost:11434/v1
    model: hermes3:latest

# ── Fallback Model ────────────────────────────────────────────────────
# Automatic provider failover when primary is unavailable.
# Uncomment and configure to enable. Triggers on rate limits (429),
# overload (529), service errors (503), or connection failures.
#
# Supported providers:
#   openrouter   (OPENROUTER_API_KEY)  — routes to any model
#   openai-codex (OAuth — hermes login) — OpenAI Codex
#   nous         (OAuth — hermes login) — Nous Portal
#   zai          (ZAI_API_KEY)         — Z.AI / GLM
#   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
#   minimax      (MINIMAX_API_KEY)     — MiniMax
#   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
#
# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
#
# fallback_model:
#   provider: openrouter
#   model: anthropic/claude-sonnet-4
#
# ── Smart Model Routing ────────────────────────────────────────────────
# Optional cheap-vs-strong routing for simple turns.
# Keeps the primary model for complex work, but can route short/simple
# messages to a cheaper model across providers.
#
# smart_model_routing:
#   enabled: true
#   max_simple_chars: 160
#   max_simple_words: 28
#   cheap_model:
#     provider: openrouter
#     model: google/gemini-2.5-flash

# Sovereign Orchestration MCP Server
# Exposes: Gitea API, Task Queue, Playbook Engine
mcp_servers:
  orchestration:
    command: "/Users/apayne/.hermes/hermes-agent/venv/bin/python3"
    args: ["/Users/apayne/.hermes/hermes-agent/tools/orchestration_mcp_server.py"]
    env: {}
    timeout: 120