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>
terminal.cwd "." resolved against each process's working directory, so
the dashboard's sandbox mounted / (the whole disk, writable) and the
gateway's mounted ~/.hermes (including .env). Point it at ~/hermes.
The cua-driver symlink in ~/.hermes/skills made Hermes give each sandbox
a temp copy of the skills and delete the previous copy, emptying running
sandboxes' skills (hermes-agent #53630). Read Cua's pack through
skills.external_dirs and remove the symlink.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Hermes's OpenRouter code treats Claude models it doesn't list as
reasoning-mandatory and drops the guardian's "reasoning off" for Haiku
5.5, which then sometimes spends the 16-token budget thinking and
returns nothing, escalating the command to the user. Send
extra_body.reasoning {effort: none} for the approval task; replays of
the failing commands went 21/21 correct.
Also create ~/hermes, the folder the Hermex Bot Chat session works in.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`hermes config get` fills in and masks ${VAR} references, so the Karakeep
MCP entry (env KARAKEEP_API_KEY: ${KARAKEEP_API_KEY}) never matched and
every deploy re-set it and restarted the gateway. It also prints defaults
for unset keys and exits 1 for keys without one. Compare against
~/.hermes/config.yaml itself instead.
`hermes gateway restart` without a terminal refuses while anything is
running unless given --yes (docs, reference/cli-commands); the failed
handler left the gateway restarting under launchd but the play failed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Hermes can search and read bookmarks, create them, tag them and add them
to lists from Telegram. Per Karakeep's MCP README and Hermes's MCP docs:
- the official server image (pinned 0.34.1) runs in a throwaway Podman
container (`podman run -i --rm`), started on first use and stopped
after 10 idle minutes;
- only search/read/create/tag/add-to-list tools are registered (no update
or delete); trust: full because Karakeep doesn't mark its search tools
read-only;
- the API key is in the vault, written to ~/.hermes/.env via the new
hermes_env_secrets, and passed into the container by name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
bad2426 failed silently: over SSH `sysadminctl -autologin set` can't reach
the loginwindow session agent and fails with SACSetAutoLoginPassword
error:22 (rc 0), leaving autoLoginUser set without /etc/kcpassword. Per
gulasz101/homelab-2nd#178 (measured 2026-11-09), run it inside the console
user's session with `launchctl asuser <uid>`, password on stdin. It accepts
wrong passwords, so check the vault password with `dscl -authonly` first
(as brunerd's setAutoLogin.sh does). Idempotency now checks autoLoginUser
and /etc/kcpassword instead of the status text, which never matched.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The Mac powers back on after a power cut but stopped at the login window,
so nothing that needs a login session (dashboard, Podman VM for Hermes's
sandbox, BlueBubbles, Beeper) came back. Turn on automatic login with
sysadminctl, using phil's password from the vault. FileVault is off, so it
works unattended. User accepted the physical-access trade-off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`podman machine start` exits once the VM is up, and launchd then killed the
VM processes left in the job's process group, so a VM started by the job
stopped ~20 s later. Keep them with AbandonProcessGroup, and reload the job
when its plist changes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Non-interactively, `hermes config get` prints only the default for a key
that isn't in config.yaml, so an unset key can't be detected and the play
kept trying (and failing) to unset terminal.cwd. Set it to Hermes's own
default "." instead and drop the unset branch.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`hermes config get` writes "Config key not set" to stderr and Hermes's
default to stdout, so terminal.cwd: null looked set ("."), the play tried
to unset it again and `unset` failed on the missing key.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The VM resize in a92d4c1 worked but left the VM stopped: a VM started from
an Ansible task is stopped when the task ends. Nothing started the VM at
login either, so after a reboot Hermes's sandbox stayed down.
- launchd job local.podman-machine runs `podman machine start` at login;
the resize now starts the VM through it and waits until it's running.
- Hermes setting changes also restart the dashboard, which keeps its own
copy of the settings (it kept logging the old /workspace cwd).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Via hermes_settings (now compared structurally, with null = unset, and a
gateway restart on change):
- timezone America/Denver (was unset)
- auth.adopt_external_logins false: never borrow Claude Code's login
- terminal.cwd unset: stops the /workspace warnings (#140527)
- agent.disabled_toolsets [kanban]: unused, 25 KB of tool schema per call
- skills.write_approval true
- approvals.deny: force-push, curl|sh, dd to devices (docs' examples)
- streaming.enabled true, stt.local.model small
- terminal.container_memory 3072, inside a 4 GB Podman VM (was 2 GB VM
with a 5 GB container limit), set by a new podman task
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Hermes has no auto-update for itself, and /update from Telegram can leave
a launchd gateway offline. Instead, a no-agent Hermes cron job runs
`hermes update --check` on Mondays at 09:07 and messages Telegram only when
a new stable release is out (a failing check sends an error alert).
Adds hermes_cron_jobs (scripts in files/hermes-scripts/, copied to
~/.hermes/scripts/; jobs created when missing) so the deal checker can
follow the same pattern.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds a small hermes_settings map that Ansible checks with
`hermes config get` and fixes with `hermes config set`, leaving the rest
of config.yaml to Hermes (its updates migrate that file).
First setting: updates.pre_update_backup: full (was false), so every
`hermes update` zips ~/.hermes first. Rollback isn't supported once a new
version has written state.db, so the backup is the way back.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The dashboard used to be started by hand as `serve --host 0.0.0.0`, so it
was reachable from the LAN and didn't survive a reboot or a Hermes update.
Now, following Hermes's docs:
- launchd agent local.hermes-dashboard runs `hermes dashboard` on
127.0.0.1:9119 (KeepAlive, --skip-build since `hermes update` builds it).
- Tailscale Serve publishes it on https://cogitator-02.porgy-porgy.ts.net,
tailnet only. No module exists for Serve; the task reads
`serve status --json` and only sets it when it differs.
- Login: scrypt password hash and a real signing secret from the vault
(the old secret was the literal text "$(openssl rand -base64 32)"); the
plaintext password line is removed from .env since it overrides the hash.
- After Serve is set, the play checks /api/status demands the basic login;
if not, it turns Serve off and fails.
- Hermes's Python no longer needs a firewall exception, so that's gone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- pmset: never sleep, no disk sleep, restart after a power cut, wake on
network. The Mac had sleep 1 and only stayed up because BlueBubbles runs
caffeinate.
- Application firewall on, keeping signed software allowed automatically,
stealth and block-all off. Hermes's ad hoc signed Python (dashboard on
9119) is allowed explicitly, since an unattended Mac blocks unsigned
programs silently.
- Local id_ed25519.pub in phil's authorized_keys (already there).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
cogitator-02 is an Apple Silicon Mac on the tailnet running Hermes Agent.
It gets a `mac` group and mac.yml, kept apart from site.yml so it never
runs with the server's deploys (PLAYBOOK=mac.yml bin/deploy).
The mac role starts by recording the Homebrew taps, formulae and casks
already installed (present only, never upgrades or removes), so the first
run changes nothing.
No passwordless sudo on the Mac: Hermes runs as phil and takes commands
over Telegram. Ansible's sudo password is vault_cogitator02.become_password
and only tasks with become: true use it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>