fix(docker): seed s6 gateway state for legacy run cmd (#34829)

* fix(docker): seed s6 gateway state for legacy run cmd

* fix(docker): honor no-supervise during legacy gateway migration

---------

Co-authored-by: Donovan Yohan <donovan-yohan@users.noreply.github.com>

hermes_cli/container_boot.py

@@ -24,7 +24,7 @@ import logging
 import os
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Literal
+from typing import Literal, Sequence
 
 log = logging.getLogger(__name__)
 
@@ -57,6 +57,7 @@ def reconcile_profile_gateways(
     hermes_home: Path,
     scandir: Path,
     dry_run: bool = False,
+    container_argv: Sequence[str] | None = None,
 ) -> list[ReconcileAction]:
     """Recreate s6 service registrations for every persistent profile.
 
@@ -82,6 +83,8 @@ def reconcile_profile_gateways(
             directories are created at ``<scandir>/gateway-<profile>/``.
         dry_run: When True, walk and return the action list without
             touching the filesystem. For tests and `--dry-run` debug.
+        container_argv: Optional container PID 1 argv override. Production
+            reads ``/proc/1/cmdline``; tests inject it directly.
 
     Returns:
         One :class:`ReconcileAction` per profile, in this order:
@@ -93,8 +96,15 @@ def reconcile_profile_gateways(
     # populated the root profile dir. The slot exists so
     # ``hermes gateway start`` (no ``-p``) has somewhere to land;
     # auto-up only when the prior state was "running" (same rule as
-    # named profiles).
+    # named profiles). If the container was launched with the legacy
-    default_prior_state = _read_prior_state(hermes_home)
+    # `gateway run` command and no state exists yet, seed that intent
+    # as `running` so the s6 reconciler preserves the pre-s6 behavior.
+    legacy_default_state = _maybe_migrate_legacy_gateway_run_state(
+        hermes_home,
+        container_argv=container_argv,
+        dry_run=dry_run,
+    )
+    default_prior_state = legacy_default_state or _read_prior_state(hermes_home)
     default_should_start = default_prior_state in _AUTOSTART_STATES
     if not dry_run:
         _cleanup_stale_runtime_files(hermes_home)
@@ -147,6 +157,66 @@ def reconcile_profile_gateways(
     return actions
 
 
+def _maybe_migrate_legacy_gateway_run_state(
+    hermes_home: Path,
+    *,
+    container_argv: Sequence[str] | None,
+    dry_run: bool,
+) -> str | None:
+    """Seed root gateway_state for pre-s6 `gateway run` containers.
+
+    The tini image let Docker users run the gateway as the container
+    command (`docker run ... gateway run`). After the s6 migration,
+    profile gateways are restored from persisted gateway_state.json; a
+    legacy container with no state file would therefore register the
+    default service down and never start. Only synthesize state when no
+    root gateway_state.json exists so explicit stopped/failed states keep
+    winning across restarts.
+    """
+    state_file = hermes_home / "gateway_state.json"
+    if state_file.exists():
+        return None
+
+    if os.environ.get("HERMES_GATEWAY_NO_SUPERVISE", "").lower() in ("1", "true", "yes"):
+        return None
+
+    argv = tuple(container_argv) if container_argv is not None else _read_container_argv()
+    if not _is_legacy_gateway_run_request(argv):
+        return None
+
+    if not dry_run:
+        import time
+        state_file.write_text(json.dumps({
+            "gateway_state": "running",
+            "timestamp": int(time.time()),
+            "migrated_from": "legacy-container-cmd",
+        }) + "\n")
+    return "running"
+
+
+def _read_container_argv() -> tuple[str, ...]:
+    """Best-effort read of the container PID 1 argv."""
+    try:
+        raw = Path("/proc/1/cmdline").read_bytes()
+    except OSError:
+        return ()
+    return tuple(part.decode("utf-8", "replace") for part in raw.split(b"\0") if part)
+
+
+def _is_legacy_gateway_run_request(argv: Sequence[str]) -> bool:
+    """Return True for Docker commands equivalent to `gateway run`."""
+    args = list(argv)
+    if args and Path(args[0]).name == "init":
+        args = args[1:]
+    if args and args[0].endswith("main-wrapper.sh"):
+        args = args[1:]
+    if args and Path(args[0]).name == "hermes":
+        args = args[1:]
+    if "--no-supervise" in args:
+        return False
+    return len(args) >= 2 and args[0] == "gateway" and args[1] == "run"
+
+
 def _read_prior_state(profile_dir: Path) -> str | None:
     """Read gateway_state.json's ``gateway_state`` field, or None if
     missing or unparseable. Unparseable counts as "no prior state" so

tests/hermes_cli/test_container_boot.py

@@ -484,6 +484,88 @@ def test_default_slot_autostarts_when_root_state_running(tmp_path: Path) -> None
     assert not (scandir / "gateway-default" / "down").exists()
 
 
+@pytest.mark.parametrize(
+    "container_argv",
+    [
+        ("gateway", "run"),
+        ("/init", "/opt/hermes/docker/main-wrapper.sh", "gateway", "run"),
+    ],
+)
+def test_legacy_gateway_run_cmd_seeds_default_running_state(
+    tmp_path: Path,
+    container_argv: tuple[str, ...],
+) -> None:
+    """Pre-s6 Docker users often ran `gateway run` as the container
+    command. With no persisted gateway_state.json yet, s6 reconciliation
+    must migrate that legacy intent into a running default gateway slot."""
+    scandir = tmp_path / "run-service"; scandir.mkdir()
+
+    actions = reconcile_profile_gateways(
+        hermes_home=tmp_path,
+        scandir=scandir,
+        dry_run=False,
+        container_argv=container_argv,
+    )
+
+    default_action = next(a for a in actions if a.profile == "default")
+    assert default_action.prior_state == "running"
+    assert default_action.action == "started"
+    assert not (scandir / "gateway-default" / "down").exists()
+    state = json.loads((tmp_path / "gateway_state.json").read_text())
+    assert state["gateway_state"] == "running"
+    assert state["migrated_from"] == "legacy-container-cmd"
+
+
+@pytest.mark.parametrize(
+    "container_argv",
+    [
+        ("gateway", "run", "--no-supervise"),
+        ("/init", "/opt/hermes/docker/main-wrapper.sh", "gateway", "run", "--no-supervise"),
+    ],
+)
+def test_legacy_gateway_run_no_supervise_does_not_seed_s6_state(
+    tmp_path: Path,
+    container_argv: tuple[str, ...],
+) -> None:
+    """`gateway run --no-supervise` is an explicit opt-out from s6 migration."""
+    scandir = tmp_path / "run-service"; scandir.mkdir()
+
+    actions = reconcile_profile_gateways(
+        hermes_home=tmp_path,
+        scandir=scandir,
+        dry_run=False,
+        container_argv=container_argv,
+    )
+
+    default_action = next(a for a in actions if a.profile == "default")
+    assert default_action.prior_state is None
+    assert default_action.action == "registered"
+    assert (scandir / "gateway-default" / "down").exists()
+    assert not (tmp_path / "gateway_state.json").exists()
+
+
+def test_legacy_gateway_run_env_no_supervise_does_not_seed_s6_state(
+    tmp_path: Path,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Env opt-out matches the CLI `--no-supervise` flag."""
+    scandir = tmp_path / "run-service"; scandir.mkdir()
+    monkeypatch.setenv("HERMES_GATEWAY_NO_SUPERVISE", "1")
+
+    actions = reconcile_profile_gateways(
+        hermes_home=tmp_path,
+        scandir=scandir,
+        dry_run=False,
+        container_argv=("gateway", "run"),
+    )
+
+    default_action = next(a for a in actions if a.profile == "default")
+    assert default_action.prior_state is None
+    assert default_action.action == "registered"
+    assert (scandir / "gateway-default" / "down").exists()
+    assert not (tmp_path / "gateway_state.json").exists()
+
+
 def test_default_slot_does_not_autostart_when_root_state_stopped(
     tmp_path: Path,
 ) -> None:
@@ -491,12 +573,17 @@ def test_default_slot_does_not_autostart_when_root_state_stopped(
     _seed_default_root(tmp_path, state="stopped")
 
     actions = reconcile_profile_gateways(
-        hermes_home=tmp_path, scandir=scandir, dry_run=False,
+        hermes_home=tmp_path,
+        scandir=scandir,
+        dry_run=False,
+        container_argv=("gateway", "run"),
     )
 
     default_action = next(a for a in actions if a.profile == "default")
     assert default_action.action == "registered"
     assert (scandir / "gateway-default" / "down").exists()
+    state = json.loads((tmp_path / "gateway_state.json").read_text())
+    assert state["gateway_state"] == "stopped"
 
 
 def test_default_slot_does_not_autostart_when_root_state_startup_failed(