Podman reports the sandbox image as docker.io/nousresearch/...; Hermes compares image names as text, so the short name made it delete and recreate the sandbox on every reuse. Use the full name. Hermes 0.23.1 looks for Chromium in chrome-linux/, but the ARM64 image ships chrome-linux-arm64/ (hermes-agent #153626), so browser tools said there was no Chromium. Mount a folder with a chrome-linux/chrome script that runs the image's Chromium. Tested in a fresh sandbox: the probe finds it and browser_exec loads pages. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
223 lines
11 KiB
YAML
223 lines
11 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
|
|
|
|
# The one host folder Hermes's sandbox sees (mounted at /workspace).
|
|
hermes_workspace: "{{ ansible_user_dir }}/hermes"
|
|
# Mounted into the sandbox for the browser (terminal.docker_volumes below).
|
|
hermes_sandbox_chromium: "{{ ansible_user_dir }}/.hermes/sandbox-chromium"
|
|
|
|
# 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
|
|
# The host folder mounted into the sandbox at /workspace
|
|
# (terminal.docker_mount_cwd_to_workspace). "." meant each process's own
|
|
# working directory: / for the dashboard (the whole disk) and ~/.hermes for
|
|
# the gateway (its .env with the API keys). A container path such as
|
|
# /workspace made the host log a warning every few seconds (#140527).
|
|
terminal.cwd: "{{ hermes_workspace }}"
|
|
# Podman reports images by their full name, and Hermes compares names as
|
|
# text: the short name made it delete the sandbox on every reuse.
|
|
terminal.docker_image: docker.io/nousresearch/hermes-sandbox:desktop
|
|
# Hermes 0.23.1 looks for Chromium in chrome-linux/; the ARM64 image ships
|
|
# chrome-linux-arm64/, so the browser said there was none (hermes-agent
|
|
# #153626). The mounted folder (roles/mac/files/sandbox-chromium) holds a
|
|
# chrome-linux/chrome script that runs the image's own Chromium.
|
|
terminal.docker_volumes:
|
|
- "{{ hermes_sandbox_chromium }}:/home/pn/.cache/ms-playwright:ro"
|
|
terminal.container_memory: 3072 # MB; must fit in the Podman VM (podman_machine_memory)
|
|
# kanban: multi-agent boards (unused here); its 14 tools were 25 KB of the
|
|
# 65 KB of tool definitions sent with every message.
|
|
# web: Hermes's built-in web_search/web_extract (was the free Brave API,
|
|
# rate-limited). Search and page fetching go through Kagi's MCP server.
|
|
agent.disabled_toolsets: [kanban, web]
|
|
skills.write_approval: true # skills Hermes writes wait for your approval
|
|
# Cua's skill pack, read in place instead of through the symlink
|
|
# `cua-driver skills install` puts in ~/.hermes/skills (removed by the
|
|
# settings tasks). A symlink there makes Hermes give each sandbox a temp
|
|
# copy of the skills, and deleting the old copy empties running sandboxes'
|
|
# skills (hermes-agent #53630).
|
|
skills.external_dirs: ["~/.cua-driver/skills"]
|
|
# 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"). Vision, voice
|
|
# and /review stay on the chat model.
|
|
# Short-answer tasks turn reasoning off and allow only a few tokens (the
|
|
# approval guardian: 16, titles: 64). GLM-5.3 Flash can't turn reasoning off
|
|
# (OpenRouter: reasoning mandatory), spends the budget thinking and returns
|
|
# nothing, so the guardian escalated every command to you. Haiku 5.5 can
|
|
# turn reasoning off, but Hermes's OpenRouter code treats Claude models it
|
|
# doesn't list as reasoning-mandatory and drops the "off" (hermes-agent
|
|
# #134761). Haiku then sometimes thinks through the 16 tokens on longer
|
|
# commands. extra_body.reasoning is sent to OpenRouter as written.
|
|
auxiliary.approval.provider: openrouter
|
|
auxiliary.approval.model: anthropic/claude-haiku-5.5
|
|
auxiliary.approval.extra_body: {reasoning: {effort: none}}
|
|
auxiliary.title_generation.provider: openrouter
|
|
auxiliary.title_generation.model: anthropic/claude-haiku-5.5
|
|
auxiliary.memory_query_rewrite.provider: openrouter
|
|
auxiliary.memory_query_rewrite.model: anthropic/claude-haiku-5.5
|
|
auxiliary.mcp.provider: openrouter
|
|
auxiliary.mcp.model: anthropic/claude-haiku-5.5
|
|
# Longer tasks: GLM-5.3 Flash is the cheapest model with credible Hermes
|
|
# scores; its slow first token doesn't matter here.
|
|
auxiliary.compression.provider: openrouter
|
|
auxiliary.compression.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
|
|
|
|
mcp_servers.karakeep: "{{ hermes_mcp_karakeep }}"
|
|
mcp_servers.kagi: "{{ hermes_mcp_kagi }}"
|
|
|
|
# MCP servers. Each stdio server runs in a throwaway Podman container (not on
|
|
# the Mac itself); secrets come from ~/.hermes/.env (hermes_env_secrets) and
|
|
# are passed to the container by name, never on the command line.
|
|
hermes_mcp_podman_args: [run, -i, --rm]
|
|
|
|
# Karakeep (bookmarks): search/read, create, tag, add to list. No update or
|
|
# delete tools are registered. trust: full because Karakeep doesn't mark its
|
|
# search tools read-only, so "untrusted" would ask before every search.
|
|
# github.com/karakeep-app/karakeep/tree/main/apps/mcp
|
|
hermes_karakeep_mcp_image: ghcr.io/karakeep-app/karakeep-mcp:0.34.1
|
|
hermes_mcp_karakeep:
|
|
command: /opt/podman/bin/podman
|
|
args: "{{ hermes_mcp_podman_args + ['-e', 'KARAKEEP_API_ADDR', '-e', 'KARAKEEP_API_KEY', hermes_karakeep_mcp_image] }}"
|
|
env:
|
|
KARAKEEP_API_ADDR: "https://{{ subdomains.bookmarks }}"
|
|
KARAKEEP_API_KEY: "${KARAKEEP_API_KEY}"
|
|
lazy: true # start the container on first use
|
|
idle_timeout_seconds: 600 # and stop it after 10 idle minutes
|
|
tools:
|
|
include:
|
|
- search-bookmarks
|
|
- get-bookmark
|
|
- get-bookmark-content
|
|
- get-bookmark-lists
|
|
- get-lists
|
|
- get-list
|
|
- get-list-bookmarks
|
|
- get-tags
|
|
- get-tag
|
|
- get-tag-bookmarks
|
|
- create-bookmark
|
|
- attach-tag-to-bookmark
|
|
- add-bookmark-to-list
|
|
resources: false
|
|
prompts: false
|
|
|
|
# Kagi (web search and page fetching), Kagi's own hosted MCP server: nothing
|
|
# runs on the Mac. Paid API, $12/1k searches and $4/1k pages, prepaid with a
|
|
# monthly cap set in Kagi. Both tools are marked read-only, so "untrusted"
|
|
# never asks. https://kagi.com/api/docs/openapi/section/mcp
|
|
hermes_mcp_kagi:
|
|
url: https://mcp.kagi.com/mcp
|
|
headers:
|
|
Authorization: "Bearer ${KAGI_API_KEY}"
|
|
trust: untrusted
|
|
tools:
|
|
resources: false
|
|
prompts: false
|
|
|
|
# Secrets written to ~/.hermes/.env (single-quoted), from the vault.
|
|
hermes_env_secrets:
|
|
KARAKEEP_API_KEY: "{{ vault_cogitator02.karakeep_api_key }}"
|
|
KAGI_API_KEY: "{{ vault_cogitator02.kagi_api_key }}"
|
|
|
|
# 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.
|