Compare commits

...

1 Commits

Author SHA1 Message Date
alt-glitch
611b89c2a7 feat(nix): container-aware CLI — auto-route hermes chat into managed container
When container.enable = true in the NixOS module, running 'hermes chat'
on the host now automatically execs into the managed container via
docker/podman exec. This means the interactive CLI runs in the same
environment as the gateway service, with access to all container-installed
packages and tools.

Implementation:
- NixOS activation script writes .container-mode metadata file to
  HERMES_HOME with backend, container_name, and hermes_bin path
- File is removed when container mode is disabled (nixos-rebuild switch)
- hermes_cli/config.py: _is_inside_container() detects Docker/Podman
  indicators (/.dockerenv, /run/.containerenv, cgroup)
- hermes_cli/config.py: get_container_exec_info() reads .container-mode
  metadata, returns None when already inside a container
- hermes_cli/main.py: _exec_in_container() validates the container is
  running, then os.execvp() replaces the process with the container exec
- cmd_chat intercepts before normal flow, checks container info, execs

Safety:
- --host flag bypasses container routing (run on host regardless)
- Falls back to host CLI if: container runtime not found, container not
  running, inspect fails, or any detection error
- Strips --host from forwarded args (not meaningful inside container)
- Already-inside-container detection prevents infinite exec loops

Closes #7380
2026-04-11 06:15:44 +05:30
5 changed files with 435 additions and 0 deletions

View File

@@ -141,6 +141,68 @@ def managed_error(action: str = "modify configuration"):
print(format_managed_message(action), file=sys.stderr)
# =============================================================================
# Container-aware CLI (NixOS container mode)
# =============================================================================
def _is_inside_container() -> bool:
"""Detect if we're already running inside a Docker/Podman container."""
# Standard Docker/Podman indicators
if os.path.exists("/.dockerenv"):
return True
# Podman uses /run/.containerenv
if os.path.exists("/run/.containerenv"):
return True
# Check cgroup for container runtime evidence (works for both Docker & Podman)
try:
with open("/proc/1/cgroup", "r") as f:
cgroup = f.read()
if "docker" in cgroup or "podman" in cgroup or "/lxc/" in cgroup:
return True
except (OSError, IOError):
pass
return False
def get_container_exec_info() -> Optional[dict]:
"""Read container mode metadata from HERMES_HOME/.container-mode.
Returns a dict with keys: backend, container_name, hermes_bin
or None if container mode is not active or we're already inside the container.
The .container-mode file is written by the NixOS activation script when
container.enable = true. It tells the host CLI to exec into the container
instead of running locally.
"""
if _is_inside_container():
return None
container_mode_file = get_hermes_home() / ".container-mode"
if not container_mode_file.exists():
return None
try:
info = {}
with open(container_mode_file, "r") as f:
for line in f:
line = line.strip()
if "=" in line and not line.startswith("#"):
key, _, value = line.partition("=")
info[key.strip()] = value.strip()
backend = info.get("backend", "docker")
container_name = info.get("container_name", "hermes-agent")
hermes_bin = info.get("hermes_bin", "/data/current-package/bin/hermes")
return {
"backend": backend,
"container_name": container_name,
"hermes_bin": hermes_bin,
}
except (OSError, IOError):
return None
# =============================================================================
# Config paths
# =============================================================================

View File

@@ -528,6 +528,56 @@ def _resolve_last_cli_session() -> Optional[str]:
return None
def _exec_in_container(container_info: dict, cli_args: list):
"""Replace the current process with a command inside the managed container.
Uses os.execvp to hand off to docker/podman exec, preserving the TTY
so the interactive CLI works seamlessly inside the container.
Args:
container_info: dict with backend, container_name, hermes_bin
cli_args: the original CLI arguments (everything after 'hermes')
"""
import shutil
import subprocess
backend = container_info["backend"]
container_name = container_info["container_name"]
hermes_bin = container_info["hermes_bin"]
# Find the container runtime on PATH
runtime = shutil.which(backend)
if not runtime:
print(f"Warning: {backend} not found on PATH, falling back to host CLI.",
file=sys.stderr)
return # Fall through to normal CLI
# Check if the container is actually running
try:
result = subprocess.run(
[runtime, "inspect", "--format", "{{.State.Running}}", container_name],
capture_output=True, text=True, timeout=5
)
if result.returncode != 0 or result.stdout.strip().lower() != "true":
print(f"Warning: container '{container_name}' is not running, falling back to host CLI.",
file=sys.stderr)
return
except (subprocess.TimeoutExpired, OSError):
return # Fall through on any error
# Filter out --host flag from forwarded args (it's not meaningful inside)
forwarded_args = [a for a in cli_args if a != "--host"]
# Build the exec command
exec_cmd = [runtime, "exec", "-it", container_name, hermes_bin] + forwarded_args
print(f"Routing to container '{container_name}' via {backend}...",
file=sys.stderr)
# Replace the current process — this never returns on success
os.execvp(runtime, exec_cmd)
def _resolve_session_by_name_or_id(name_or_id: str) -> Optional[str]:
"""Resolve a session name (title) or ID to a session ID.
@@ -556,6 +606,21 @@ def _resolve_session_by_name_or_id(name_or_id: str) -> Optional[str]:
def cmd_chat(args):
"""Run interactive chat CLI."""
# ── Container-aware routing ──────────────────────────────────────────
# When NixOS container mode is active and we're on the host, exec into
# the managed container instead of running locally. --host bypasses this.
if not getattr(args, "host", False):
try:
from hermes_cli.config import get_container_exec_info
container_info = get_container_exec_info()
if container_info:
_exec_in_container(container_info, sys.argv[1:])
# _exec_in_container calls os.execvp which replaces the process.
# If we get here, the exec failed.
sys.exit(1)
except Exception:
pass # Fall through to normal CLI on any detection error
# Resolve --continue into --resume with the latest CLI session or by name
continue_val = getattr(args, "continue_last", None)
if continue_val and not getattr(args, "resume", None):
@@ -4386,6 +4451,12 @@ For more help on a command:
default=None,
help="Session source tag for filtering (default: cli). Use 'tool' for third-party integrations that should not appear in user session lists."
)
chat_parser.add_argument(
"--host",
action="store_true",
default=False,
help="Run on the host even when NixOS container mode is active (bypass container exec)"
)
chat_parser.set_defaults(func=cmd_chat)
# =========================================================================

View File

@@ -611,6 +611,22 @@
chown ${cfg.user}:${cfg.group} ${cfg.stateDir}/.hermes/.managed
chmod 0644 ${cfg.stateDir}/.hermes/.managed
# Container mode metadata tells the host CLI to exec into the
# container instead of running locally. Removed when container mode
# is disabled so the host CLI falls back to native execution.
${if cfg.container.enable then ''
cat > ${cfg.stateDir}/.hermes/.container-mode <<'HERMES_CONTAINER_MODE_EOF'
# Written by NixOS activation script. Do not edit manually.
backend=${cfg.container.backend}
container_name=${containerName}
hermes_bin=${containerDataDir}/current-package/bin/hermes
HERMES_CONTAINER_MODE_EOF
chown ${cfg.user}:${cfg.group} ${cfg.stateDir}/.hermes/.container-mode
chmod 0644 ${cfg.stateDir}/.hermes/.container-mode
'' else ''
rm -f ${cfg.stateDir}/.hermes/.container-mode
''}
# Seed auth file if provided
${lib.optionalString (cfg.authFile != null) ''
${if cfg.authFileForceOverwrite then ''

View File

@@ -0,0 +1,275 @@
"""Tests for container-aware CLI routing (NixOS container mode).
When container.enable = true in the NixOS module, the activation script
writes a .container-mode metadata file. The host CLI detects this and
execs into the container instead of running locally.
"""
import os
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import MagicMock, patch
import pytest
from hermes_cli.config import (
_is_inside_container,
get_container_exec_info,
)
# =============================================================================
# _is_inside_container
# =============================================================================
def test_is_inside_container_dockerenv(tmp_path):
"""Detects /.dockerenv marker file."""
with patch("os.path.exists") as mock_exists:
mock_exists.side_effect = lambda p: p == "/.dockerenv"
assert _is_inside_container() is True
def test_is_inside_container_containerenv(tmp_path):
"""Detects Podman's /run/.containerenv marker."""
with patch("os.path.exists") as mock_exists:
mock_exists.side_effect = lambda p: p == "/run/.containerenv"
assert _is_inside_container() is True
def test_is_inside_container_cgroup_docker():
"""Detects 'docker' in /proc/1/cgroup."""
with patch("os.path.exists", return_value=False), \
patch("builtins.open", create=True) as mock_open:
mock_open.return_value.__enter__ = lambda s: s
mock_open.return_value.__exit__ = MagicMock(return_value=False)
mock_open.return_value.read = MagicMock(
return_value="12:memory:/docker/abc123\n"
)
assert _is_inside_container() is True
def test_is_inside_container_false_on_host():
"""Returns False when none of the container indicators are present."""
with patch("os.path.exists", return_value=False), \
patch("builtins.open", side_effect=OSError("no such file")):
assert _is_inside_container() is False
# =============================================================================
# get_container_exec_info
# =============================================================================
@pytest.fixture
def container_env(tmp_path, monkeypatch):
"""Set up a fake HERMES_HOME with .container-mode file."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
container_mode = hermes_home / ".container-mode"
container_mode.write_text(
"# Written by NixOS activation script. Do not edit manually.\n"
"backend=podman\n"
"container_name=hermes-agent\n"
"hermes_bin=/data/current-package/bin/hermes\n"
)
return hermes_home
def test_get_container_exec_info_returns_metadata(container_env):
"""Reads .container-mode and returns backend/name/bin."""
with patch("hermes_cli.config._is_inside_container", return_value=False):
info = get_container_exec_info()
assert info is not None
assert info["backend"] == "podman"
assert info["container_name"] == "hermes-agent"
assert info["hermes_bin"] == "/data/current-package/bin/hermes"
def test_get_container_exec_info_none_inside_container(container_env):
"""Returns None when we're already inside a container."""
with patch("hermes_cli.config._is_inside_container", return_value=True):
info = get_container_exec_info()
assert info is None
def test_get_container_exec_info_none_without_file(tmp_path, monkeypatch):
"""Returns None when .container-mode doesn't exist (native mode)."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
with patch("hermes_cli.config._is_inside_container", return_value=False):
info = get_container_exec_info()
assert info is None
def test_get_container_exec_info_defaults():
"""Falls back to defaults for missing keys."""
import tempfile
with tempfile.TemporaryDirectory() as tmpdir:
hermes_home = Path(tmpdir) / ".hermes"
hermes_home.mkdir()
(hermes_home / ".container-mode").write_text(
"# minimal file with no keys\n"
)
with patch("hermes_cli.config._is_inside_container", return_value=False), \
patch("hermes_cli.config.get_hermes_home", return_value=hermes_home):
info = get_container_exec_info()
assert info is not None
assert info["backend"] == "docker"
assert info["container_name"] == "hermes-agent"
assert info["hermes_bin"] == "/data/current-package/bin/hermes"
def test_get_container_exec_info_docker_backend(container_env):
"""Correctly reads docker backend."""
(container_env / ".container-mode").write_text(
"backend=docker\n"
"container_name=hermes-custom\n"
"hermes_bin=/opt/hermes/bin/hermes\n"
)
with patch("hermes_cli.config._is_inside_container", return_value=False):
info = get_container_exec_info()
assert info["backend"] == "docker"
assert info["container_name"] == "hermes-custom"
assert info["hermes_bin"] == "/opt/hermes/bin/hermes"
# =============================================================================
# _exec_in_container
# =============================================================================
def test_exec_in_container_calls_execvp():
"""Verifies os.execvp is called with the correct command."""
from hermes_cli.main import _exec_in_container
container_info = {
"backend": "podman",
"container_name": "hermes-agent",
"hermes_bin": "/data/current-package/bin/hermes",
}
with patch("shutil.which", return_value="/usr/bin/podman"), \
patch("subprocess.run") as mock_run, \
patch("os.execvp") as mock_exec:
# Simulate running container
mock_result = MagicMock()
mock_result.returncode = 0
mock_result.stdout = "true\n"
mock_run.return_value = mock_result
_exec_in_container(container_info, ["chat", "-m", "claude-sonnet-4"])
mock_exec.assert_called_once_with(
"/usr/bin/podman",
["/usr/bin/podman", "exec", "-it", "hermes-agent",
"/data/current-package/bin/hermes", "chat", "-m", "claude-sonnet-4"]
)
def test_exec_in_container_strips_host_flag():
"""The --host flag is not forwarded into the container."""
from hermes_cli.main import _exec_in_container
container_info = {
"backend": "podman",
"container_name": "hermes-agent",
"hermes_bin": "/data/current-package/bin/hermes",
}
with patch("shutil.which", return_value="/usr/bin/podman"), \
patch("subprocess.run") as mock_run, \
patch("os.execvp") as mock_exec:
mock_result = MagicMock()
mock_result.returncode = 0
mock_result.stdout = "true\n"
mock_run.return_value = mock_result
_exec_in_container(container_info, ["chat", "--host", "-q", "hello"])
# --host should be stripped
exec_args = mock_exec.call_args[0][1]
assert "--host" not in exec_args
assert "-q" in exec_args
assert "hello" in exec_args
def test_exec_in_container_fallback_no_runtime(capsys):
"""Falls back gracefully when container runtime is not found."""
from hermes_cli.main import _exec_in_container
container_info = {
"backend": "podman",
"container_name": "hermes-agent",
"hermes_bin": "/data/current-package/bin/hermes",
}
with patch("shutil.which", return_value=None), \
patch("os.execvp") as mock_exec:
_exec_in_container(container_info, ["chat"])
# Should NOT call execvp — graceful fallback
mock_exec.assert_not_called()
captured = capsys.readouterr()
assert "not found on PATH" in captured.err
def test_exec_in_container_fallback_container_not_running(capsys):
"""Falls back when container exists but is not running."""
from hermes_cli.main import _exec_in_container
container_info = {
"backend": "docker",
"container_name": "hermes-agent",
"hermes_bin": "/data/current-package/bin/hermes",
}
with patch("shutil.which", return_value="/usr/bin/docker"), \
patch("subprocess.run") as mock_run, \
patch("os.execvp") as mock_exec:
mock_result = MagicMock()
mock_result.returncode = 0
mock_result.stdout = "false\n"
mock_run.return_value = mock_result
_exec_in_container(container_info, ["chat"])
mock_exec.assert_not_called()
captured = capsys.readouterr()
assert "not running" in captured.err
def test_exec_in_container_fallback_inspect_fails():
"""Falls back when docker inspect fails entirely."""
from hermes_cli.main import _exec_in_container
container_info = {
"backend": "docker",
"container_name": "hermes-agent",
"hermes_bin": "/data/current-package/bin/hermes",
}
with patch("shutil.which", return_value="/usr/bin/docker"), \
patch("subprocess.run") as mock_run, \
patch("os.execvp") as mock_exec:
mock_result = MagicMock()
mock_result.returncode = 1
mock_result.stdout = ""
mock_run.return_value = mock_result
_exec_in_container(container_info, ["chat"])
mock_exec.assert_not_called()

View File

@@ -122,6 +122,17 @@ services.hermes-agent.environmentFiles = [ "/var/lib/hermes/env" ];
Setting `addToSystemPackages = true` does two things: puts the `hermes` CLI on your system PATH **and** sets `HERMES_HOME` system-wide so the interactive CLI shares state (sessions, skills, cron) with the gateway service. Without it, running `hermes` in your shell creates a separate `~/.hermes/` directory.
:::
:::info Container-aware CLI
When `container.enable = true` and `addToSystemPackages = true`, running `hermes chat` on the host **automatically routes into the managed container**. This means your interactive CLI session runs inside the same environment as the gateway service — with access to all container-installed packages and tools.
- The routing is transparent: `hermes chat` detects container mode and does `podman exec` / `docker exec` under the hood
- All CLI flags are forwarded: `-m`, `--resume`, `--query`, etc. work as normal
- Use `hermes chat --host` to bypass container routing and run directly on the host
- If the container isn't running, the CLI falls back to host execution automatically
Other `hermes` subcommands (`version`, `config`, `sessions`, `setup`) always run on the host since they only need access to shared state files.
:::
### Verify It Works
After `nixos-rebuild switch`, check that the service is running: