feat: add profiles — run multiple isolated Hermes instances (#3681)

Each profile is a fully independent HERMES_HOME with its own config,
API keys, memory, sessions, skills, gateway, cron, and state.db.

Core module: hermes_cli/profiles.py (~900 lines)
  - Profile CRUD: create, delete, list, show, rename
  - Three clone levels: blank, --clone (config), --clone-all (everything)
  - Export/import: tar.gz archive for backup and migration
  - Wrapper alias scripts (~/.local/bin/<name>)
  - Collision detection for alias names
  - Sticky default via ~/.hermes/active_profile
  - Skill seeding via subprocess (handles module-level caching)
  - Auto-stop gateway on delete with disable-before-stop for services
  - Tab completion generation for bash and zsh

CLI integration (hermes_cli/main.py):
  - _apply_profile_override(): pre-import -p/--profile flag + sticky default
  - Full 'hermes profile' subcommand: list, use, create, delete, show,
    alias, rename, export, import
  - 'hermes completion bash/zsh' command
  - Multi-profile skill sync in hermes update

Display (cli.py, banner.py, gateway/run.py):
  - CLI prompt: 'coder ❯' when using a non-default profile
  - Banner shows profile name
  - Gateway startup log includes profile name

Gateway safety:
  - Token locks: Discord, Slack, WhatsApp, Signal (extends Telegram pattern)
  - Port conflict detection: API server, webhook adapter

Diagnostics (hermes_cli/doctor.py):
  - Profile health section: lists profiles, checks config, .env, aliases
  - Orphan alias detection: warns when wrapper points to deleted profile

Tests (tests/hermes_cli/test_profiles.py):
  - 71 automated tests covering: validation, CRUD, clone levels, rename,
    export/import, active profile, isolation, alias collision, completion
  - Full suite: 6760 passed, 0 new failures

Documentation:
  - website/docs/user-guide/profiles.md: full user guide (12 sections)
  - website/docs/reference/profile-commands.md: command reference (12 commands)
  - website/docs/reference/faq.md: 6 profile FAQ entries
  - website/sidebars.ts: navigation updated
This commit is contained in:
Teknium
2026-03-29 10:41:20 -07:00
committed by GitHub
parent 0df4d1278e
commit f6db1b27ba
19 changed files with 2788 additions and 2 deletions

View File

@@ -1261,6 +1261,17 @@ class APIServerAdapter(BasePlatformAdapter):
self._app.router.add_post("/api/jobs/{job_id}/resume", self._handle_resume_job)
self._app.router.add_post("/api/jobs/{job_id}/run", self._handle_run_job)
# Port conflict detection — fail fast if port is already in use
import socket as _socket
try:
with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:
_s.settimeout(1)
_s.connect(('127.0.0.1', self._port))
logger.error('[%s] Port %d already in use. Set a different port in config.yaml: platforms.api_server.port', self.name, self._port)
return False
except (ConnectionRefusedError, OSError):
pass # port is free
self._runner = web.AppRunner(self._app)
await self._runner.setup()
self._site = web.TCPSite(self._runner, self._host, self._port)

View File

@@ -486,6 +486,16 @@ class DiscordAdapter(BasePlatformAdapter):
return False
try:
# Acquire scoped lock to prevent duplicate bot token usage
from gateway.status import acquire_scoped_lock
acquired, existing = acquire_scoped_lock('discord-bot-token', self.config.token, metadata={'platform': 'discord'})
if not acquired:
owner_pid = existing.get('pid') if isinstance(existing, dict) else None
message = f'Discord bot token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
logger.error('[%s] %s', self.name, message)
self._set_fatal_error('discord_token_lock', message, retryable=False)
return False
# Set up intents -- members intent needed for username-to-ID resolution
intents = Intents.default()
intents.message_content = True
@@ -638,6 +648,14 @@ class DiscordAdapter(BasePlatformAdapter):
self._running = False
self._client = None
self._ready_event.clear()
# Release the token lock
try:
from gateway.status import release_scoped_lock
release_scoped_lock('discord-bot-token', self.config.token)
except Exception:
pass
logger.info("[%s] Disconnected", self.name)
async def send(

View File

@@ -184,6 +184,8 @@ class SignalAdapter(BasePlatformAdapter):
self._recent_sent_timestamps: set = set()
self._max_recent_timestamps = 50
self._phone_lock_identity: Optional[str] = None
logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
self.http_url, _redact_phone(self.account),
"enabled" if self.group_allow_from else "disabled")
@@ -198,6 +200,29 @@ class SignalAdapter(BasePlatformAdapter):
logger.error("Signal: SIGNAL_HTTP_URL and SIGNAL_ACCOUNT are required")
return False
# Acquire scoped lock to prevent duplicate Signal listeners for the same phone
try:
from gateway.status import acquire_scoped_lock
self._phone_lock_identity = self.account
acquired, existing = acquire_scoped_lock(
"signal-phone",
self._phone_lock_identity,
metadata={"platform": self.platform.value},
)
if not acquired:
owner_pid = existing.get("pid") if isinstance(existing, dict) else None
message = (
"Another local Hermes gateway is already using this Signal account"
+ (f" (PID {owner_pid})." if owner_pid else ".")
+ " Stop the other gateway before starting a second Signal listener."
)
logger.error("Signal: %s", message)
self._set_fatal_error("signal_phone_lock", message, retryable=False)
return False
except Exception as e:
logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
self.client = httpx.AsyncClient(timeout=30.0)
# Health check — verify signal-cli daemon is reachable
@@ -245,6 +270,14 @@ class SignalAdapter(BasePlatformAdapter):
await self.client.aclose()
self.client = None
if self._phone_lock_identity:
try:
from gateway.status import release_scoped_lock
release_scoped_lock("signal-phone", self._phone_lock_identity)
except Exception as e:
logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
self._phone_lock_identity = None
logger.info("Signal: disconnected")
# ------------------------------------------------------------------

View File

@@ -93,6 +93,16 @@ class SlackAdapter(BasePlatformAdapter):
return False
try:
# Acquire scoped lock to prevent duplicate app token usage
from gateway.status import acquire_scoped_lock
acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
if not acquired:
owner_pid = existing.get('pid') if isinstance(existing, dict) else None
message = f'Slack app token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
logger.error('[%s] %s', self.name, message)
self._set_fatal_error('slack_token_lock', message, retryable=False)
return False
self._app = AsyncApp(token=bot_token)
# Get our own bot user ID for mention detection
@@ -138,6 +148,16 @@ class SlackAdapter(BasePlatformAdapter):
except Exception as e: # pragma: no cover - defensive logging
logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
self._running = False
# Release the token lock
try:
from gateway.status import release_scoped_lock
app_token = os.getenv("SLACK_APP_TOKEN")
if app_token:
release_scoped_lock('slack-app-token', app_token)
except Exception:
pass
logger.info("[Slack] Disconnected")
async def send(

View File

@@ -118,6 +118,17 @@ class WebhookAdapter(BasePlatformAdapter):
app.router.add_get("/health", self._handle_health)
app.router.add_post("/webhooks/{route_name}", self._handle_webhook)
# Port conflict detection — fail fast if port is already in use
import socket as _socket
try:
with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:
_s.settimeout(1)
_s.connect(('127.0.0.1', self._port))
logger.error('[webhook] Port %d already in use. Set a different port in config.yaml: platforms.webhook.port', self._port)
return False
except (ConnectionRefusedError, OSError):
pass # port is free
self._runner = web.AppRunner(app)
await self._runner.setup()
site = web.TCPSite(self._runner, self._host, self._port)

View File

@@ -142,6 +142,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
self._bridge_log_fh = None
self._bridge_log: Optional[Path] = None
self._poll_task: Optional[asyncio.Task] = None
self._session_lock_identity: Optional[str] = None
async def connect(self) -> bool:
"""
@@ -160,6 +161,29 @@ class WhatsAppAdapter(BasePlatformAdapter):
logger.info("[%s] Bridge found at %s", self.name, bridge_path)
# Acquire scoped lock to prevent duplicate sessions
try:
from gateway.status import acquire_scoped_lock
self._session_lock_identity = str(self._session_path)
acquired, existing = acquire_scoped_lock(
"whatsapp-session",
self._session_lock_identity,
metadata={"platform": self.platform.value},
)
if not acquired:
owner_pid = existing.get("pid") if isinstance(existing, dict) else None
message = (
"Another local Hermes gateway is already using this WhatsApp session"
+ (f" (PID {owner_pid})." if owner_pid else ".")
+ " Stop the other gateway before starting a second WhatsApp bridge."
)
logger.error("[%s] %s", self.name, message)
self._set_fatal_error("whatsapp_session_lock", message, retryable=False)
return False
except Exception as e:
logger.warning("[%s] Could not acquire session lock (non-fatal): %s", self.name, e)
# Auto-install npm dependencies if node_modules doesn't exist
bridge_dir = bridge_path.parent
if not (bridge_dir / "node_modules").exists():
@@ -313,6 +337,12 @@ class WhatsAppAdapter(BasePlatformAdapter):
return True
except Exception as e:
if self._session_lock_identity:
try:
from gateway.status import release_scoped_lock
release_scoped_lock("whatsapp-session", self._session_lock_identity)
except Exception:
pass
logger.error("[%s] Failed to start bridge: %s", self.name, e, exc_info=True)
self._close_bridge_log()
return False
@@ -371,9 +401,17 @@ class WhatsAppAdapter(BasePlatformAdapter):
# Bridge was not started by us, don't kill it
print(f"[{self.name}] Disconnecting (external bridge left running)")
if self._session_lock_identity:
try:
from gateway.status import release_scoped_lock
release_scoped_lock("whatsapp-session", self._session_lock_identity)
except Exception as e:
logger.warning("[%s] Error releasing WhatsApp session lock: %s", self.name, e, exc_info=True)
self._mark_disconnected()
self._bridge_process = None
self._close_bridge_log()
self._session_lock_identity = None
print(f"[{self.name}] Disconnected")
async def send(

View File

@@ -959,6 +959,13 @@ class GatewayRunner:
"""
logger.info("Starting Hermes Gateway...")
logger.info("Session storage: %s", self.config.sessions_dir)
try:
from hermes_cli.profiles import get_active_profile_name
_profile = get_active_profile_name()
if _profile and _profile != "default":
logger.info("Active profile: %s", _profile)
except Exception:
pass
try:
from gateway.status import write_runtime_status
write_runtime_status(gateway_state="starting", exit_reason=None)