dotfiles/hermes/install.sh

#!/usr/bin/env sh
# hermes/install.sh — install Hermes Agent by Nous Research, and point it at
# the covert-gpt LiteLLM gateway.
#
# WHY: Hermes requires Python 3.11+ and creates a self-contained venv at
# ~/.hermes. The official installer handles the complexity of managing its
# own uv-based Python environment. This module simply runs the official
# installer with --skip-setup so it completes in non-interactive mode.
# Everything under $HOME, survives Kasm redeploys.
#
# It then merges hermes/gateway.yaml into ~/.hermes/config.yaml, so a fresh box
# gets a Hermes that can actually talk to the gateway. Without that step Hermes
# installs and then points at nothing — the asymmetry mcp-config/ does not have,
# since opencode rebuilds its config from Gitea on every shell via sync.sh.
#
# No secrets are handled here: gateway.yaml references the key by NAME
# (key_env: LITELLM_KEY) and mcp-config/sync.sh exports it. Run
# mcp-config/install.sh first.
set -eu

SCRIPT_DIR="$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)"
REPO_ROOT="$(dirname -- "$SCRIPT_DIR")"

# shellcheck source=../lib/fetch.sh
. "$REPO_ROOT/lib/fetch.sh"

say() { printf '%s\n' "$*" >&2; }

# Hermes Agent version (synced with PyPI/npm).
HERMES_VERSION="v0.18.2"

# --- 1. the binary --------------------------------------------------------
# Check if hermes is already installed at the correct version using the
# .versions stamp pattern from bin/install.sh. NOTE: this only skips the
# DOWNLOAD — the config merge below still runs, so a config fix ships to an
# already-installed box on the next bootstrap.
if [ -x "$HOME/.local/bin/hermes" ] && [ -f "$HOME/.local/bin/.versions/hermes" ] && [ "$(cat "$HOME/.local/bin/.versions/hermes")" = "$HERMES_VERSION" ]; then
  say "hermes-agent $HERMES_VERSION already installed."
else
  say "Installing hermes-agent via official installer..."
  # Run the official installer in non-interactive mode, skipping the setup
  # wizard. The installer creates ~/.hermes/venvs/hermes with its own
  # uv-managed Python.
  curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash -s -- --non-interactive --skip-setup

  # Verify installation by checking the binary exists AND produces expected output.
  if command -v hermes >/dev/null 2>&1; then
    mkdir -p "$HOME/.local/bin/.versions"
    printf '%s\n' "$HERMES_VERSION" >"$HOME/.local/bin/.versions/hermes"
    say "Installed hermes-agent $HERMES_VERSION successfully."
  else
    say "ERROR: hermes CLI not found after install"
    exit 1
  fi
fi

# --- 2. point it at the gateway -------------------------------------------
# Merge hermes/gateway.yaml into ~/.hermes/config.yaml. Idempotent, and
# deliberately NON-DESTRUCTIVE: config.yaml is a large personal file
# (personalities, display prefs, toolsets) that Hermes also rewrites itself, so
# this replaces ONLY the covert-gpt custom_providers entry and never rewrites
# the rest. model.default / model.provider are seeded only when unset, so a
# deliberate model choice is preserved across bootstraps.
#
# PyYAML is needed to merge. Prefer the system python3; fall back to Hermes' own
# venv, which always has it. If neither works the config step is skipped with a
# warning rather than failing bootstrap — the binary is still installed, and a
# missing provider is a far smaller problem than a broken box.
GATEWAY_YAML="$SCRIPT_DIR/gateway.yaml"
HERMES_CONFIG="$HOME/.hermes/config.yaml"

PY=""
for _c in python3 "$HOME/.hermes/venvs/hermes/bin/python" "$HOME/.hermes/hermes-agent/venv/bin/python"; do
  if command -v "$_c" >/dev/null 2>&1 && "$_c" -c 'import yaml' >/dev/null 2>&1; then PY="$_c"; break; fi
done

if [ -z "$PY" ]; then
  say "WARNING: no python3 with PyYAML found — skipping Hermes gateway config."
  say "         Install PyYAML and re-run $0 to finish wiring the gateway."
elif [ ! -f "$GATEWAY_YAML" ]; then
  say "WARNING: $GATEWAY_YAML missing — skipping Hermes gateway config."
else
  HERMES_GATEWAY_YAML="$GATEWAY_YAML" HERMES_CONFIG_PATH="$HERMES_CONFIG" "$PY" - <<'PYEOF'
import os, sys, tempfile
import yaml

gw_path = os.environ["HERMES_GATEWAY_YAML"]
cfg_path = os.environ["HERMES_CONFIG_PATH"]

with open(gw_path) as f:
    gw = yaml.safe_load(f) or {}
entries = gw.get("custom_providers") or []
if not entries:
    print("hermes: gateway.yaml has no custom_providers — nothing to do", file=sys.stderr)
    raise SystemExit(0)

cfg = {}
if os.path.exists(cfg_path):
    try:
        with open(cfg_path) as f:
            cfg = yaml.safe_load(f) or {}
    except Exception as e:
        # A corrupt config is the user's to fix; never overwrite it blind.
        print(f"hermes: {cfg_path} is not valid YAML ({e}) — skipping", file=sys.stderr)
        raise SystemExit(0)
if not isinstance(cfg, dict):
    print(f"hermes: {cfg_path} is not a mapping — skipping", file=sys.stderr)
    raise SystemExit(0)

existing = cfg.get("custom_providers")
if not isinstance(existing, list):
    existing = []

changed = []
for entry in entries:
    name = entry.get("name")
    if not name:
        continue
    for i, cur in enumerate(existing):
        if isinstance(cur, dict) and cur.get("name") == name:
            if cur != entry:
                existing[i] = entry
                changed.append(f"updated custom_providers[{name}]")
            break
    else:
        existing.append(entry)
        changed.append(f"added custom_providers[{name}]")
cfg["custom_providers"] = existing

# `default` is a BARE model id and `provider` is the custom:<name> form; both
# are the user's to change, so they are seeded on a fresh box and otherwise left
# alone — EXCEPT to migrate the old masquerade, below.
primary = entries[0]["name"]
model = cfg.get("model")
if not isinstance(model, dict):
    model = {}

gw_url = (entries[0].get("base_url") or "").rstrip("/")
cur_provider = (model.get("provider") or "").strip()
cur_base = (model.get("base_url") or "").rstrip("/")

# MIGRATE the old masquerade: `provider: openrouter` + `base_url: <this
# gateway>`. That shape routed requests here but left the picker listing
# openrouter.ai's catalog, so leaving it in place would silently preserve the
# exact bug this module exists to fix. `base_url` pointing at OUR gateway is the
# fingerprint — a genuine OpenRouter user never has that. Any OTHER provider is
# a deliberate choice and is never touched.
if gw_url and cur_base == gw_url and cur_provider in ("", "openrouter", "custom"):
    if cur_provider != f"custom:{primary}":
        model["provider"] = f"custom:{primary}"
        changed.append(
            f"migrated model.provider {cur_provider or '<unset>'} -> custom:{primary}"
        )
elif not cur_provider:
    model["provider"] = f"custom:{primary}"
    changed.append(f"set model.provider=custom:{primary}")

if not model.get("default"):
    first_model = next(iter((entries[0].get("models") or {})), None)
    if first_model:
        model["default"] = first_model
        changed.append(f"set model.default={first_model}")

# model.base_url is ignored once a named custom provider supplies it, and a
# stale value here is an active footgun — drop it if it points at this gateway.
if gw_url and cur_base == gw_url:
    model.pop("base_url", None)
    changed.append("removed dead model.base_url")
cfg["model"] = model

if not changed:
    print("hermes: gateway config already current", file=sys.stderr)
    raise SystemExit(0)

d = os.path.dirname(cfg_path) or "."
os.makedirs(d, exist_ok=True)
fd, tmp = tempfile.mkstemp(dir=d)
with os.fdopen(fd, "w") as f:
    yaml.safe_dump(cfg, f, sort_keys=False, default_flow_style=False, allow_unicode=True)
os.chmod(tmp, 0o600)
os.replace(tmp, cfg_path)
for c in changed:
    print(f"hermes: {c}", file=sys.stderr)
PYEOF

  # The provider is useless without the key. mcp-config/sync.sh exports it; warn
  # rather than fail, since bootstrap ordering may put mcp-config after this.
  if [ -z "${LITELLM_KEY:-}" ] && [ ! -f "$HOME/.config/mcp-sync/key" ]; then
    say "NOTE: LITELLM_KEY is unset and ~/.config/mcp-sync/key is missing."
    say "      Run mcp-config/install.sh, or Hermes will 401 against the gateway."
  fi
  # The old OpenRouter masquerade actively breaks the model picker (it lists
  # openrouter.ai's catalog, not the gateway's), so flag it if it lingers.
  if [ -n "${OPENROUTER_API_KEY:-}" ] && [ "${OPENROUTER_API_KEY:-}" = "${LITELLM_KEY:-x}" ]; then
    say "NOTE: OPENROUTER_API_KEY is set to the LiteLLM key in your environment."
    say "      That is the old masquerade; unset it in ~/.hermes/.env so the"
    say "      model picker shows the gateway's models instead of openrouter.ai's."
  fi
fi