actual-setup skill

Actual Computer Setup Skill

Sets up actual.inc (Actual Computer) as a Hermes inference provider. Actual turns the user's own hardware into a private inference cluster and exposes an OpenAI-compatible API two ways: a hosted end-to-end-encrypted relay at https://api.actual.inc (authenticated with an ac_ key), and a local on-device daemon at http://127.0.0.1:8080 (no auth on loopback). This skill does not install the Actual daemon for the user — device authorization requires a human in a browser.

When to Use

• User wants to add actual.inc as an inference provider (cloud relay or local).
• User has an ac_ key and wants Hermes routed through their Actual cluster.
• User wants fully-local, on-device inference via the Actual daemon.
• Troubleshooting: Actual requests failing with cryptic 400s or empty streams.

Prerequisites

aliases actual-computer, actualcomputer, aci). Do NOT configure Actual as a customproviders / providers.actual. entry on current Hermes — the built-in provider owns the name and handles base-url normalization, the Responses transport, and local no-auth automatically.

• Hermes has first-class actual provider support (provider id actual,

https://actual.inc/user/keys.

• Relay mode: an Actual account and an ac_ inference key from

(curl -fsSL "https://actual.inc/install" | bash) and completed device authorization by running actual once and opening the printed https://actual.inc/device?code=... URL in a browser. Relay that URL to the user and WAIT — never invent an email or authorize on their behalf. Codes expire in 5 minutes; re-run actual for a fresh one.

• Local mode: the user has installed the daemon

How to Run

Relay / API mode

append ACTUALAPIKEY=ac_... to ~/.hermes/.env.

1. Put the key in .env (secrets only — never config.yaml):

1. Verify the key and discover models with terminal:

curl -s https://api.actual.inc/v1/models -H "Authorization: Bearer $ACTUAL_API_KEY"

1. Select provider + model:

hermes config set model.provider actual
   hermes config set model.default "MODEL_ID_FROM_DISCOVERY"

1. Verify end-to-end:

hermes chat -Q -q "Reply with exactly: ACTUAL_OK" --provider actual -m MODEL_ID

Local mode

1. Human has installed + authorized the daemon (see Prerequisites).
2. Download and load a model (scriptable once authorized):

actual models search "qwen2.5 0.5b instruct gguf" --limit 8 --no-prompt
   # Downloads REQUIRE an explicit quantization (409 ambiguous_model_download otherwise):
   actual models download "Qwen/Qwen2.5-0.5B-Instruct-GGUF/Q4_K_M"
   actual models list        # note the INSTALLED name (differs from download id)
   actual models load "qwen2.5-0.5b-instruct-q4_k_m"   # load by installed name

built-in provider into local no-auth mode automatically — no key needed: append ACTUALBASEURL=http://127.0.0.1:8080 to ~/.hermes/.env, then:

1. Point Hermes at the daemon. ACTUALBASEURL with a loopback host flips the

hermes config set model.provider actual
   hermes config set model.default "INSTALLED_MODEL_NAME"

1. Verify (reduced toolset — see context-window pitfall below):

hermes chat -Q -q "Reply with exactly: LOCAL_OK" --provider actual -m INSTALLED_NAME -t file,web

Quick Reference

Pitfalls

Actual's SGLang/vLLM backends accept only none/low/medium/high/max; xhigh/ultra used to fail with a cryptic Expecting value: line 1 column 1 (char 0) (a wrapped HTTP 400). The built-in provider clamps xhigh→high and ultra→max on the wire. If a request still 400s this way on an old Hermes, set a per-model cap: agent.reasoning_overrides.: high in config.yaml.

1. reasoningeffort trap (handled by Hermes since the first-class provider).**

is ~26k tokens of schemas plus a ~9k-token system prompt. A model loaded with a 32k context overflows before the first turn, and llama.cpp-family servers emit a bare data: [DONE] — Hermes reports Provider returned an empty stream with no finishreason. This is NOT an SSE bug. Fixes: restrict tools (-t file,web), load the model with a larger nctx, or pick a >=64k-context model for the full toolset. Upstream tracking: #51448 (do not file new issues; add evidence there). Related but distinct: #65631 (HTTP-200 SSE carrying a 400), #56516 (reasoning-only streams).

1. Context-window overflow on small local models. Hermes' default toolset

repo/QUANT and 409s without an explicit quantization; actual models load takes the INSTALLED name from actual models list.

1. Download ids vs installed names. actual models download takes

emit thinking in a separate reasoning field and can burn a small maxtokens entirely on reasoning. Give generous maxtokens before assuming failure.

1. Reasoning models returning empty content. GLM/Qwen reasoning variants

(pre first-class support) wrote providers.actual.* config blocks. On current Hermes the built-in provider wins the name; stale custom blocks are ignored or conflict. Remove them and use the env vars + model.provider flow above.

1. Do not create a custom provider named actual. Older setup guides

Verification

# Relay:
hermes chat -Q -q "Reply with exactly: ACTUAL_OK" --provider actual -m MODEL
# Local (small model — reduced toolset):
hermes chat -Q -q "Reply with exactly: LOCAL_OK" --provider actual -m MODEL -t file,web
# Provider status (local no-auth shows key_source=local-offline):
hermes status

For other OpenAI-compatible clients (e.g. OpenCode), see references/opencode.md.