Files
ansible/group_vars/mac/main.yml
T
PhilandClaude Opus 5.5 a0e49f4670 Mac: Hermes models (Sol chat, cheap side tasks) and monthly model review
Models, from the Nov 2026 review (Nous Hermes Index, OpenRouter data):
- chat: openai/gpt-6.1-sol (user's pick), reasoning high (was ultra)
- side tasks (compression, approval, titles, mcp, memory query rewrite,
  curator, mail monitor) and unpinned cron: z-ai/glm-5.3-flash
- subagents: deepseek/deepseek-v4.1-flash
- /model aliases: deepseek, haiku
agent.reasoning_effort needs --force (hermes-agent #140221), so settings
can list keys in hermes_settings_force. `config get` exits 1 for unset
keys without a default; that now reads as unset, not a failure.

hermes-model-review: monthly cron job on Sol (pinned, high effort,
continuity) that redoes this research and sends keep/change
recommendations as Ansible keys to Telegram. A script injects the live
model setup and 30-day usage into its prompt. hermes_cron_jobs gains
model/provider, reasoning_effort and continuity.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 08:13:00 -07:00

132 lines
6.7 KiB
YAML

# cogitator-02: an Apple Silicon Mac on the tailnet. Ansible manages it as
# phil; only tasks that set `become: true` use sudo.
ansible_python_interpreter: /usr/bin/python3
ansible_become_password: "{{ vault_cogitator02.become_password }}"
homebrew_taps:
- beeper/tap
homebrew_formulae:
- beeper/tap/bbctl
homebrew_casks:
- beeper
- claude-code
# Power settings (pmset, AC power). The Mac had `sleep 1` and only stayed up
# because BlueBubbles runs caffeinate; this keeps it up on its own.
mac_pmset:
sleep: 0 # never sleep
disksleep: 0 # never spin down disks
autorestart: 1 # power back on after a power cut
womp: 1 # wake on network access
# Hermes's web dashboard: a launchd service listening on 127.0.0.1 only,
# published to the tailnet over HTTPS by Tailscale Serve.
hermes_dashboard_port: 9119
hermes_dashboard_url: "https://{{ ansible_host }}"
hermes_dashboard_username: admin
# Individual Hermes settings, set with `hermes config set`. The rest of
# ~/.hermes/config.yaml stays Hermes's own (its updates migrate that file).
hermes_settings:
updates.pre_update_backup: full # zip of ~/.hermes before every update
timezone: America/Denver # cron schedules and the time in the prompt
# Never borrow Claude Code's login: subscription use outside Anthropic's own
# apps breaks its terms, and refreshing it can break Claude Code's login.
auth.adopt_external_logins: false
# Hermes's default. /workspace (a container path) made the host log a
# warning every few seconds (hermes-agent #140527); with the docker backend
# a host cwd never becomes the container's working directory anyway.
terminal.cwd: .
terminal.container_memory: 3072 # MB; must fit in the Podman VM (podman_machine_memory)
# Kanban is for multi-agent boards (unused here) and its 14 tools were 25 KB
# of the 65 KB of tool definitions sent with every message.
agent.disabled_toolsets: [kanban]
skills.write_approval: true # skills Hermes writes wait for your approval
# Never run these, even in the sandbox and even under /yolo (examples from
# Hermes's hardening guide). Case-insensitive globs over the whole command.
approvals.deny:
- "git push --force*"
- "*curl*|*sh*"
- "dd if=* of=/dev/*"
streaming.enabled: true # replies stream into Telegram as they're written
stt.local.model: small # voice notes: more accurate than base
# Models (OpenRouter), from the Nov 2026 review of Nous's Hermes Index
# (portal.nousresearch.com/bench): chat on GPT-6.1 Sol (best value of the
# premium models there), background work on cheap models.
model.default: openai/gpt-6.1-sol
agent.reasoning_effort: high # the level Nous benchmarks at (was ultra)
# /model deepseek or /model haiku in Telegram; add --once for one reply.
model_aliases.deepseek: {model: deepseek/deepseek-v4.1-flash, provider: openrouter}
model_aliases.haiku: {model: anthropic/claude-haiku-5.5, provider: openrouter}
# Side tasks would otherwise run on the chat model ("auto"). GLM-5.3 Flash
# is the cheapest model with credible Hermes scores; its slow first token
# doesn't matter here. Vision, voice and /review stay on the chat model.
auxiliary.compression.provider: openrouter
auxiliary.compression.model: z-ai/glm-5.3-flash
auxiliary.approval.provider: openrouter
auxiliary.approval.model: z-ai/glm-5.3-flash
auxiliary.title_generation.provider: openrouter
auxiliary.title_generation.model: z-ai/glm-5.3-flash
auxiliary.mcp.provider: openrouter
auxiliary.mcp.model: z-ai/glm-5.3-flash
auxiliary.memory_query_rewrite.provider: openrouter
auxiliary.memory_query_rewrite.model: z-ai/glm-5.3-flash
auxiliary.curator.provider: openrouter
auxiliary.curator.model: z-ai/glm-5.3-flash
auxiliary.monitor.provider: openrouter
auxiliary.monitor.model: z-ai/glm-5.3-flash
# Unpinned cron jobs. Per-job reasoning effort: set --reasoning-effort low
# when creating agent jobs (there's no global cron setting for it).
cron.model_provider: openrouter
cron.model: z-ai/glm-5.3-flash
# Subagents: DeepSeek V4.1 Flash does shell work better than the other
# cheap models (TerminalBench 17.5 vs GPT-6 Luna 6.3).
delegation.provider: openrouter
delegation.model: deepseek/deepseek-v4.1-flash
# Keys `hermes config set` refuses without --force although Hermes reads them
# (agent.reasoning_effort: hermes-agent #140221).
hermes_settings_force: [agent.reasoning_effort]
# Podman VM that runs Hermes's sandbox containers.
podman_machine_memory: 4096 # MB
# Hermes cron jobs. `script` is a file in roles/mac/files/hermes-scripts/,
# copied to ~/.hermes/scripts/ (with an agent job its output is injected into
# the prompt). Optional: model + provider (pin), reasoning_effort, continuity.
# Jobs are created when missing; to change one, remove it in Hermes
# (`hermes cron remove <name>`) and redeploy.
hermes_cron_jobs:
- name: hermes-update-notice
schedule: "7 9 * * 1" # Mondays 09:07
script: hermes-update-notice.sh
no_agent: true # just the script's output, no model
deliver: telegram
- name: hermes-model-review
schedule: "7 9 1 * *" # 1st of the month, 09:07
script: hermes-model-context.sh # current setup + usage, injected into the prompt
model: openai/gpt-6.1-sol # a report you act on: strong model, pinned
provider: openrouter
reasoning_effort: high
continuity: true # sees last month's report, says what changed
deliver: telegram
prompt: >-
Monthly review of which AI models this Hermes install should use. The
current setup and last month's usage are above. Research what changed
since last month, using primary sources where possible:
(1) Nous Research's Hermes Index, https://portal.nousresearch.com/bench
(agent tasks run inside Hermes; note it is run by Nous, who also sell
model access); (2) OpenRouter's Hermes Agent app rankings,
https://openrouter.ai/apps/hermes-agent, remembering that token volume
mostly reflects cheap automated workloads, not chat quality;
(3) current prices from https://openrouter.ai/api/v1/models; (4) notable
model releases and Hermes release notes from the past month that affect
model choice. Then, for each slot (chat model and reasoning effort,
side tasks, cron, subagents, /model aliases), say keep or change, with
the evidence, a link, and the rough monthly cost difference at the
current usage. Only recommend a change when the evidence is clearly
better, not just newer. Don't change any settings: they are managed with
Ansible, so end with the exact keys and values to change, if any. Keep
it under 300 words. If nothing should change, say so in two sentences.