Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

# Conflicts:
#	tui_gateway/server.py

hermes_cli/__init__.py

@@ -14,8 +14,8 @@ Provides subcommands for:
 import os
 import sys
 
-__version__ = "0.12.0"
-__release_date__ = "2026.4.30"
+__version__ = "0.13.0"
+__release_date__ = "2026.5.7"
 
 
 def _ensure_utf8():

hermes_cli/_parser.py

@@ -70,6 +70,9 @@ Examples:
     hermes logs --since 1h        Lines from the last hour
     hermes debug share             Upload debug report for support
     hermes update                 Update to latest version
+    hermes dashboard              Start web UI dashboard (port 9119)
+    hermes dashboard --stop       Stop running dashboard processes
+    hermes dashboard --status     List running dashboard processes
 
 For more help on a command:
     hermes <command> --help

hermes_cli/auth.py

@@ -780,42 +780,121 @@ def _auth_file_path() -> Path:
     return path
 
 
+def _global_auth_file_path() -> Optional[Path]:
+    """Return the global-root auth.json when the process is in profile mode.
+
+    Returns ``None`` when the profile and global root resolve to the same
+    directory (classic mode, or custom HERMES_HOME that is not a profile).
+    Used by read-only fallback paths so providers authed at the root are
+    visible to profile processes that haven't configured them locally.
+
+    See issue #18594 follow-up (credential_pool shadowing).
+    """
+    try:
+        from hermes_constants import get_default_hermes_root
+        global_root = get_default_hermes_root()
+    except Exception:
+        return None
+    profile_home = get_hermes_home()
+    try:
+        if profile_home.resolve(strict=False) == global_root.resolve(strict=False):
+            return None
+    except Exception:
+        if profile_home == global_root:
+            return None
+    # No pytest seat belt here: this is a pure read-only path, and
+    # ``_load_global_auth_store()`` wraps the read in a try/except so an
+    # unreadable global file can never break the profile process.  The
+    # write-side seat belt still lives on ``_auth_file_path()`` where it
+    # belongs (that's what protects the real user's auth store from being
+    # corrupted by a mis-configured test).
+    return global_root / "auth.json"
+
+
+def _load_global_auth_store() -> Dict[str, Any]:
+    """Load the global-root auth store (read-only fallback).
+
+    Returns an empty dict when no global fallback exists (classic mode,
+    or the global auth.json is absent). Never raises on missing file.
+
+    Seat belt: under pytest, refuses to read the real user's
+    ``~/.hermes/auth.json`` even when HERMES_HOME is set to a profile
+    path. The hermetic conftest does not redirect ``HOME``, so
+    ``get_default_hermes_root()`` for a profile-shaped HERMES_HOME can
+    still resolve to the real user's home on a dev machine. That would
+    leak real credentials into tests. This guard uses the unmodified
+    ``HOME`` env var (what ``os.path.expanduser('~')`` would resolve to),
+    not ``Path.home()``, because ``Path.home`` is sometimes monkeypatched
+    by fixtures that want to relocate the global root to a tmp path.
+    """
+    global_path = _global_auth_file_path()
+    if global_path is None or not global_path.exists():
+        return {}
+    if os.environ.get("PYTEST_CURRENT_TEST"):
+        real_home_env = os.environ.get("HOME", "")
+        if real_home_env:
+            real_root = Path(real_home_env) / ".hermes" / "auth.json"
+            try:
+                if global_path.resolve(strict=False) == real_root.resolve(strict=False):
+                    return {}
+            except Exception:
+                pass
+    try:
+        return _load_auth_store(global_path)
+    except Exception:
+        # A malformed global store must not break profile reads. The
+        # profile's own auth store is still authoritative.
+        return {}
+
+
 def _auth_lock_path() -> Path:
     return _auth_file_path().with_suffix(".lock")
 
 
 _auth_lock_holder = threading.local()
 
+
 @contextmanager
-def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
-    """Cross-process advisory lock for auth.json reads+writes.  Reentrant."""
-    # Reentrant: if this thread already holds the lock, just yield.
-    if getattr(_auth_lock_holder, "depth", 0) > 0:
-        _auth_lock_holder.depth += 1
+def _file_lock(
+    lock_path: Path,
+    holder: threading.local,
+    timeout_seconds: float,
+    timeout_message: str,
+):
+    """Cross-process advisory flock helper.
+
+    Reentrant per-thread via ``holder.depth``. Falls back to a depth-only
+    guard when neither ``fcntl`` nor ``msvcrt`` is available (rare).
+    Callers supply their own ``threading.local`` so independent locks
+    (e.g. profile auth.json vs shared Nous store) don't share reentrancy
+    state — that would let one lock's reentrant acquisition silently skip
+    the other's kernel-level flock.
+    """
+    if getattr(holder, "depth", 0) > 0:
+        holder.depth += 1
         try:
             yield
         finally:
-            _auth_lock_holder.depth -= 1
+            holder.depth -= 1
         return
 
-    lock_path = _auth_lock_path()
     lock_path.parent.mkdir(parents=True, exist_ok=True)
 
     if fcntl is None and msvcrt is None:
-        _auth_lock_holder.depth = 1
+        holder.depth = 1
         try:
             yield
         finally:
-            _auth_lock_holder.depth = 0
+            holder.depth = 0
         return
 
     # On Windows, msvcrt.locking needs the file to have content and the
-    # file pointer at position 0.  Ensure the lock file has at least 1 byte.
+    # file pointer at position 0. Ensure the lock file has at least 1 byte.
     if msvcrt and (not lock_path.exists() or lock_path.stat().st_size == 0):
         lock_path.write_text(" ", encoding="utf-8")
 
     with lock_path.open("r+" if msvcrt else "a+") as lock_file:
-        deadline = time.time() + max(1.0, timeout_seconds)
+        deadline = time.monotonic() + max(1.0, timeout_seconds)
         while True:
             try:
                 if fcntl:
@@ -825,15 +904,15 @@ def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
                     msvcrt.locking(lock_file.fileno(), msvcrt.LK_NBLCK, 1)
                 break
             except (BlockingIOError, OSError, PermissionError):
-                if time.time() >= deadline:
-                    raise TimeoutError("Timed out waiting for auth store lock")
+                if time.monotonic() >= deadline:
+                    raise TimeoutError(timeout_message)
                 time.sleep(0.05)
 
-        _auth_lock_holder.depth = 1
+        holder.depth = 1
         try:
             yield
         finally:
-            _auth_lock_holder.depth = 0
+            holder.depth = 0
             if fcntl:
                 fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
             elif msvcrt:
@@ -844,6 +923,25 @@ def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
                     pass
 
 
+@contextmanager
+def _auth_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
+    """Cross-process advisory lock for auth.json reads+writes.  Reentrant.
+
+    Lock ordering invariant: when this lock is held together with
+    ``_nous_shared_store_lock``, acquire ``_auth_store_lock`` FIRST
+    (outer) and the shared Nous lock SECOND (inner). All runtime
+    refresh paths follow this order; violating it risks deadlock
+    against a concurrent import on the shared store.
+    """
+    with _file_lock(
+        _auth_lock_path(),
+        _auth_lock_holder,
+        timeout_seconds,
+        "Timed out waiting for auth store lock",
+    ):
+        yield
+
+
 def _load_auth_store(auth_file: Optional[Path] = None) -> Dict[str, Any]:
     auth_file = auth_file or _auth_file_path()
     if not auth_file.exists():
@@ -887,12 +985,27 @@ def _load_auth_store(auth_file: Optional[Path] = None) -> Dict[str, Any]:
 def _save_auth_store(auth_store: Dict[str, Any]) -> Path:
     auth_file = _auth_file_path()
     auth_file.parent.mkdir(parents=True, exist_ok=True)
+    # Tighten parent dir to 0o700 so siblings can't traverse to creds.
+    # No-op on Windows (POSIX mode bits not enforced); ignore failures.
+    try:
+        os.chmod(auth_file.parent, 0o700)
+    except OSError:
+        pass
     auth_store["version"] = AUTH_STORE_VERSION
     auth_store["updated_at"] = datetime.now(timezone.utc).isoformat()
     payload = json.dumps(auth_store, indent=2) + "\n"
     tmp_path = auth_file.with_name(f"{auth_file.name}.tmp.{os.getpid()}.{uuid.uuid4().hex}")
     try:
-        with tmp_path.open("w", encoding="utf-8") as handle:
+        # Create with 0o600 atomically via os.open(O_EXCL) + fdopen to close
+        # the TOCTOU window where default umask (often 0o644) briefly exposed
+        # OAuth tokens to other local users between open() and chmod().
+        # Mirrors agent/google_oauth.py (#19673) and tools/mcp_oauth.py (#21148).
+        fd = os.open(
+            str(tmp_path),
+            os.O_WRONLY | os.O_CREAT | os.O_EXCL,
+            stat.S_IRUSR | stat.S_IWUSR,
+        )
+        with os.fdopen(fd, "w", encoding="utf-8") as handle:
             handle.write(payload)
             handle.flush()
             os.fsync(handle.fileno())
@@ -966,15 +1079,50 @@ def get_auth_provider_display_name(provider_id: str) -> str:
 
 
 def read_credential_pool(provider_id: Optional[str] = None) -> Dict[str, Any]:
-    """Return the persisted credential pool, or one provider slice."""
+    """Return the persisted credential pool, or one provider slice.
+
+    In profile mode, the profile's credential pool is authoritative. If a
+    provider has no entries in the profile, entries from the global-root
+    ``auth.json`` are used as a read-only fallback — so workers spawned in a
+    profile can see providers that were only authenticated at global scope.
+
+    Profile entries always win: the global fallback only applies per-provider
+    when the profile has zero entries for that provider. Once the user runs
+    ``hermes auth add <provider>`` inside the profile, profile entries
+    fully shadow global for that provider on the next read.
+
+    Writes always go to the profile (``write_credential_pool`` is unchanged).
+    See issue #18594 follow-up.
+    """
     auth_store = _load_auth_store()
     pool = auth_store.get("credential_pool")
     if not isinstance(pool, dict):
         pool = {}
+
+    global_pool: Dict[str, Any] = {}
+    global_store = _load_global_auth_store()
+    maybe_global_pool = global_store.get("credential_pool") if global_store else None
+    if isinstance(maybe_global_pool, dict):
+        global_pool = maybe_global_pool
+
     if provider_id is None:
-        return dict(pool)
+        merged = dict(pool)
+        for gp_key, gp_entries in global_pool.items():
+            if not isinstance(gp_entries, list) or not gp_entries:
+                continue
+            # Per-provider shadowing: profile wins whenever it has ANY entries.
+            existing = merged.get(gp_key)
+            if isinstance(existing, list) and existing:
+                continue
+            merged[gp_key] = list(gp_entries)
+        return merged
+
     provider_entries = pool.get(provider_id)
-    return list(provider_entries) if isinstance(provider_entries, list) else []
+    if isinstance(provider_entries, list) and provider_entries:
+        return list(provider_entries)
+    # Profile has no entries for this provider — fall back to global.
+    global_entries = global_pool.get(provider_id)
+    return list(global_entries) if isinstance(global_entries, list) else []
 
 
 def write_credential_pool(provider_id: str, entries: List[Dict[str, Any]]) -> Path:
@@ -1033,9 +1181,25 @@ def unsuppress_credential_source(provider_id: str, source: str) -> bool:
 
 
 def get_provider_auth_state(provider_id: str) -> Optional[Dict[str, Any]]:
-    """Return persisted auth state for a provider, or None."""
+    """Return persisted auth state for a provider, or None.
+
+    In profile mode, falls back to the global-root ``auth.json`` when the
+    profile has no state for this provider. Profile state always wins when
+    present. Writes (``_save_auth_store`` / ``persist_*_credentials``) are
+    unchanged — they still target the profile only. This mirrors
+    ``read_credential_pool``'s per-provider shadowing semantics so that
+    ``_seed_from_singletons`` can reseed a profile's credential pool from
+    global-scope provider state (e.g. a globally-authenticated Anthropic
+    OAuth or Nous device-code session). See issue #18594 follow-up.
+    """
     auth_store = _load_auth_store()
-    return _load_provider_state(auth_store, provider_id)
+    state = _load_provider_state(auth_store, provider_id)
+    if state is not None:
+        return state
+    global_store = _load_global_auth_store()
+    if not global_store:
+        return None
+    return _load_provider_state(global_store, provider_id)
 
 
 def get_active_provider() -> Optional[str]:
@@ -1405,10 +1569,33 @@ def _read_qwen_cli_tokens() -> Dict[str, Any]:
 def _save_qwen_cli_tokens(tokens: Dict[str, Any]) -> Path:
     auth_path = _qwen_cli_auth_path()
     auth_path.parent.mkdir(parents=True, exist_ok=True)
-    tmp_path = auth_path.with_suffix(".tmp")
-    tmp_path.write_text(json.dumps(tokens, indent=2, sort_keys=True) + "\n", encoding="utf-8")
-    os.chmod(tmp_path, stat.S_IRUSR | stat.S_IWUSR)
-    tmp_path.replace(auth_path)
+    try:
+        os.chmod(auth_path.parent, 0o700)
+    except OSError:
+        pass
+    # Per-process random temp suffix avoids collisions between concurrent
+    # writers and stale leftovers from a crashed prior write.
+    tmp_path = auth_path.with_name(f"{auth_path.name}.tmp.{os.getpid()}.{uuid.uuid4().hex}")
+    # Create with 0o600 atomically via os.open(O_EXCL) — closes the TOCTOU
+    # window where write_text() + post-write chmod briefly exposed tokens
+    # at process umask (typically 0o644). See #19673, #21148.
+    fd = os.open(
+        str(tmp_path),
+        os.O_WRONLY | os.O_CREAT | os.O_EXCL,
+        stat.S_IRUSR | stat.S_IWUSR,
+    )
+    try:
+        with os.fdopen(fd, "w", encoding="utf-8") as fh:
+            fh.write(json.dumps(tokens, indent=2, sort_keys=True) + "\n")
+            fh.flush()
+            os.fsync(fh.fileno())
+        atomic_replace(tmp_path, auth_path)
+    finally:
+        try:
+            if tmp_path.exists():
+                tmp_path.unlink()
+        except OSError:
+            pass
     return auth_path
 
 
@@ -1825,9 +2012,9 @@ def _spotify_wait_for_callback(
 
     thread = threading.Thread(target=server.serve_forever, kwargs={"poll_interval": 0.1}, daemon=True)
     thread.start()
-    deadline = time.time() + max(5.0, timeout_seconds)
+    deadline = time.monotonic() + max(5.0, timeout_seconds)
     try:
-        while time.time() < deadline:
+        while time.monotonic() < deadline:
             if result["code"] or result["error"]:
                 return result
             time.sleep(0.1)
@@ -2590,10 +2777,10 @@ def _poll_for_token(
     poll_interval: int,
 ) -> Dict[str, Any]:
     """Poll the token endpoint until the user approves or the code expires."""
-    deadline = time.time() + max(1, expires_in)
+    deadline = time.monotonic() + max(1, expires_in)
     current_interval = max(1, min(poll_interval, DEVICE_AUTH_POLL_INTERVAL_CAP_SECONDS))
 
-    while time.time() < deadline:
+    while time.monotonic() < deadline:
         response = client.post(
             f"{portal_base_url}/api/oauth/token",
             data={
@@ -2651,6 +2838,7 @@ def _poll_for_token(
 # -----------------------------------------------------------------------------
 
 NOUS_SHARED_STORE_FILENAME = "nous_auth.json"
+_nous_shared_lock_holder = threading.local()
 
 
 def _nous_shared_auth_dir() -> Path:
@@ -2690,6 +2878,69 @@ def _nous_shared_store_path() -> Path:
     return path
 
 
+@contextmanager
+def _nous_shared_store_lock(timeout_seconds: float = AUTH_LOCK_TIMEOUT_SECONDS):
+    """Cross-profile lock for the shared Nous OAuth store.
+
+    Lock ordering invariant: if both this and ``_auth_store_lock`` need
+    to be held, acquire ``_auth_store_lock`` FIRST. All runtime refresh
+    paths follow this order. The one exception is
+    ``_try_import_shared_nous_state``, which holds this lock alone for
+    the entire refresh+mint cycle so concurrent imports on sibling
+    profiles can't race on the single-use shared refresh token; that
+    helper must NOT be called with ``_auth_store_lock`` already held.
+    """
+    try:
+        lock_path = _nous_shared_store_path().with_suffix(".lock")
+    except RuntimeError:
+        # No HERMES_HOME yet (pre-setup): fall through without locking.
+        yield
+        return
+
+    with _file_lock(
+        lock_path,
+        _nous_shared_lock_holder,
+        timeout_seconds,
+        "Timed out waiting for shared Nous auth lock",
+    ):
+        yield
+
+
+def _merge_shared_nous_oauth_state(state: Dict[str, Any]) -> bool:
+    """Copy fresher shared OAuth tokens into a profile-local Nous state."""
+    shared = _read_shared_nous_state()
+    if not shared:
+        return False
+
+    shared_refresh = shared.get("refresh_token")
+    if not isinstance(shared_refresh, str) or not shared_refresh.strip():
+        return False
+
+    local_refresh = state.get("refresh_token")
+    shared_access_exp = _parse_iso_timestamp(shared.get("expires_at")) or 0.0
+    local_access_exp = _parse_iso_timestamp(state.get("expires_at")) or 0.0
+    refresh_changed = shared_refresh.strip() != str(local_refresh or "").strip()
+    fresher_access = shared_access_exp > local_access_exp
+    if not refresh_changed and not fresher_access:
+        return False
+
+    for key in (
+        "access_token",
+        "refresh_token",
+        "token_type",
+        "scope",
+        "client_id",
+        "portal_base_url",
+        "inference_base_url",
+        "obtained_at",
+        "expires_at",
+    ):
+        value = shared.get(key)
+        if value not in (None, ""):
+            state[key] = value
+    return True
+
+
 def _write_shared_nous_state(state: Dict[str, Any]) -> None:
     """Persist a minimal copy of the Nous OAuth state to the shared store.
 
@@ -2722,15 +2973,34 @@ def _write_shared_nous_state(state: Dict[str, Any]) -> None:
         "updated_at": datetime.now(timezone.utc).isoformat(),
     }
     try:
-        path = _nous_shared_store_path()
-        path.parent.mkdir(parents=True, exist_ok=True)
-        tmp = path.with_suffix(path.suffix + ".tmp")
-        tmp.write_text(json.dumps(shared, indent=2, sort_keys=True))
-        try:
-            os.chmod(tmp, 0o600)
-        except OSError:
-            pass
-        os.replace(tmp, path)
+        with _nous_shared_store_lock():
+            path = _nous_shared_store_path()
+            path.parent.mkdir(parents=True, exist_ok=True)
+            try:
+                os.chmod(path.parent, 0o700)
+            except OSError:
+                pass
+            tmp = path.with_name(f"{path.name}.tmp.{os.getpid()}.{uuid.uuid4().hex}")
+            # Create with 0o600 atomically via os.open(O_EXCL) — closes the TOCTOU
+            # window where write_text() + post-write chmod briefly exposed Nous
+            # refresh_token at process umask. See #19673, #21148.
+            fd = os.open(
+                str(tmp),
+                os.O_WRONLY | os.O_CREAT | os.O_EXCL,
+                stat.S_IRUSR | stat.S_IWUSR,
+            )
+            try:
+                with os.fdopen(fd, "w", encoding="utf-8") as fh:
+                    fh.write(json.dumps(shared, indent=2, sort_keys=True))
+                    fh.flush()
+                    os.fsync(fh.fileno())
+                os.replace(tmp, path)
+            finally:
+                try:
+                    if tmp.exists():
+                        tmp.unlink()
+                except OSError:
+                    pass
         _oauth_trace(
             "nous_shared_store_written",
             path=str(path),
@@ -2787,36 +3057,38 @@ def _try_import_shared_nous_state(
     etc.) — caller should then fall through to the normal device-code
     flow.
     """
-    shared = _read_shared_nous_state()
-    if not shared:
-        return None
-
-    # Build a full state dict so refresh_nous_oauth_from_state has every
-    # field it needs. force_refresh=True gets us a fresh access_token
-    # for this profile; force_mint=True gets us a fresh agent_key.
-    state: Dict[str, Any] = {
-        "access_token": shared.get("access_token"),
-        "refresh_token": shared.get("refresh_token"),
-        "client_id": shared.get("client_id") or DEFAULT_NOUS_CLIENT_ID,
-        "portal_base_url": shared.get("portal_base_url") or DEFAULT_NOUS_PORTAL_URL,
-        "inference_base_url": shared.get("inference_base_url") or DEFAULT_NOUS_INFERENCE_URL,
-        "token_type": shared.get("token_type") or "Bearer",
-        "scope": shared.get("scope") or DEFAULT_NOUS_SCOPE,
-        "obtained_at": shared.get("obtained_at"),
-        "expires_at": shared.get("expires_at"),
-        "agent_key": None,
-        "agent_key_expires_at": None,
-        "tls": {"insecure": False, "ca_bundle": None},
-    }
-
     try:
-        refreshed = refresh_nous_oauth_from_state(
-            state,
-            min_key_ttl_seconds=min_key_ttl_seconds,
-            timeout_seconds=timeout_seconds,
-            force_refresh=True,
-            force_mint=True,
-        )
+        with _nous_shared_store_lock(timeout_seconds=max(timeout_seconds + 5.0, AUTH_LOCK_TIMEOUT_SECONDS)):
+            shared = _read_shared_nous_state()
+            if not shared:
+                return None
+
+            # Build a full state dict so refresh_nous_oauth_from_state has every
+            # field it needs. force_refresh=True gets us a fresh access_token
+            # for this profile; force_mint=True gets us a fresh agent_key.
+            state: Dict[str, Any] = {
+                "access_token": shared.get("access_token"),
+                "refresh_token": shared.get("refresh_token"),
+                "client_id": shared.get("client_id") or DEFAULT_NOUS_CLIENT_ID,
+                "portal_base_url": shared.get("portal_base_url") or DEFAULT_NOUS_PORTAL_URL,
+                "inference_base_url": shared.get("inference_base_url") or DEFAULT_NOUS_INFERENCE_URL,
+                "token_type": shared.get("token_type") or "Bearer",
+                "scope": shared.get("scope") or DEFAULT_NOUS_SCOPE,
+                "obtained_at": shared.get("obtained_at"),
+                "expires_at": shared.get("expires_at"),
+                "agent_key": None,
+                "agent_key_expires_at": None,
+                "tls": {"insecure": False, "ca_bundle": None},
+            }
+
+            refreshed = refresh_nous_oauth_from_state(
+                state,
+                min_key_ttl_seconds=min_key_ttl_seconds,
+                timeout_seconds=timeout_seconds,
+                force_refresh=True,
+                force_mint=True,
+            )
+            _write_shared_nous_state(refreshed)
     except AuthError as exc:
         _oauth_trace(
             "nous_shared_import_failed",
@@ -3018,59 +3290,65 @@ def resolve_nous_access_token(
         client_id = str(state.get("client_id") or DEFAULT_NOUS_CLIENT_ID)
         verify = _resolve_verify(insecure=insecure, ca_bundle=ca_bundle, auth_state=state)
 
-        access_token = state.get("access_token")
-        refresh_token = state.get("refresh_token")
-        if not isinstance(access_token, str) or not access_token:
-            raise AuthError(
-                "No access token found for Nous Portal login.",
-                provider="nous",
-                relogin_required=True,
-            )
+        with _nous_shared_store_lock(timeout_seconds=max(timeout_seconds + 5.0, AUTH_LOCK_TIMEOUT_SECONDS)):
+            merged_shared = _merge_shared_nous_oauth_state(state)
+            access_token = state.get("access_token")
+            refresh_token = state.get("refresh_token")
+            if not isinstance(access_token, str) or not access_token:
+                raise AuthError(
+                    "No access token found for Nous Portal login.",
+                    provider="nous",
+                    relogin_required=True,
+                )
 
-        if not _is_expiring(state.get("expires_at"), refresh_skew_seconds):
-            return access_token
+            if not _is_expiring(state.get("expires_at"), refresh_skew_seconds):
+                if merged_shared:
+                    _save_provider_state(auth_store, "nous", state)
+                    _save_auth_store(auth_store)
+                return access_token
 
-        if not isinstance(refresh_token, str) or not refresh_token:
-            raise AuthError(
-                "Session expired and no refresh token is available.",
-                provider="nous",
-                relogin_required=True,
-            )
+            if not isinstance(refresh_token, str) or not refresh_token:
+                raise AuthError(
+                    "Session expired and no refresh token is available.",
+                    provider="nous",
+                    relogin_required=True,
+                )
 
-        timeout = httpx.Timeout(timeout_seconds if timeout_seconds else 15.0)
-        with httpx.Client(
-            timeout=timeout,
-            headers={"Accept": "application/json"},
-            verify=verify,
-        ) as client:
-            refreshed = _refresh_access_token(
-                client=client,
-                portal_base_url=portal_base_url,
-                client_id=client_id,
-                refresh_token=refresh_token,
-            )
+            timeout = httpx.Timeout(timeout_seconds if timeout_seconds else 15.0)
+            with httpx.Client(
+                timeout=timeout,
+                headers={"Accept": "application/json"},
+                verify=verify,
+            ) as client:
+                refreshed = _refresh_access_token(
+                    client=client,
+                    portal_base_url=portal_base_url,
+                    client_id=client_id,
+                    refresh_token=refresh_token,
+                )
 
-        now = datetime.now(timezone.utc)
-        access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
-        state["access_token"] = refreshed["access_token"]
-        state["refresh_token"] = refreshed.get("refresh_token") or refresh_token
-        state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
-        state["scope"] = refreshed.get("scope") or state.get("scope")
-        state["obtained_at"] = now.isoformat()
-        state["expires_in"] = access_ttl
-        state["expires_at"] = datetime.fromtimestamp(
-            now.timestamp() + access_ttl,
-            tz=timezone.utc,
-        ).isoformat()
-        state["portal_base_url"] = portal_base_url
-        state["client_id"] = client_id
-        state["tls"] = {
-            "insecure": verify is False,
-            "ca_bundle": verify if isinstance(verify, str) else None,
-        }
-        _save_provider_state(auth_store, "nous", state)
-        _save_auth_store(auth_store)
-        return state["access_token"]
+            now = datetime.now(timezone.utc)
+            access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
+            state["access_token"] = refreshed["access_token"]
+            state["refresh_token"] = refreshed.get("refresh_token") or refresh_token
+            state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
+            state["scope"] = refreshed.get("scope") or state.get("scope")
+            state["obtained_at"] = now.isoformat()
+            state["expires_in"] = access_ttl
+            state["expires_at"] = datetime.fromtimestamp(
+                now.timestamp() + access_ttl,
+                tz=timezone.utc,
+            ).isoformat()
+            state["portal_base_url"] = portal_base_url
+            state["client_id"] = client_id
+            state["tls"] = {
+                "insecure": verify is False,
+                "ca_bundle": verify if isinstance(verify, str) else None,
+            }
+            _save_provider_state(auth_store, "nous", state)
+            _save_auth_store(auth_store)
+            _write_shared_nous_state(state)
+            return state["access_token"]
 
 
 def refresh_nous_oauth_pure(
@@ -3338,46 +3616,53 @@ def resolve_nous_runtime_credentials(
 
             # Step 1: refresh access token if expiring
             if _is_expiring(state.get("expires_at"), ACCESS_TOKEN_REFRESH_SKEW_SECONDS):
-                if not isinstance(refresh_token, str) or not refresh_token:
-                    raise AuthError("Session expired and no refresh token is available.",
-                                    provider="nous", relogin_required=True)
+                with _nous_shared_store_lock(timeout_seconds=max(timeout_seconds + 5.0, AUTH_LOCK_TIMEOUT_SECONDS)):
+                    if _merge_shared_nous_oauth_state(state):
+                        access_token = state.get("access_token")
+                        refresh_token = state.get("refresh_token")
+                        _persist_state("post_shared_merge_access_expiring")
 
-                _oauth_trace(
-                    "refresh_start",
-                    sequence_id=sequence_id,
-                    reason="access_expiring",
-                    refresh_token_fp=_token_fingerprint(refresh_token),
-                )
-                refreshed = _refresh_access_token(
-                    client=client, portal_base_url=portal_base_url,
-                    client_id=client_id, refresh_token=refresh_token,
-                )
-                now = datetime.now(timezone.utc)
-                access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
-                previous_refresh_token = refresh_token
-                state["access_token"] = refreshed["access_token"]
-                state["refresh_token"] = refreshed.get("refresh_token") or refresh_token
-                state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
-                state["scope"] = refreshed.get("scope") or state.get("scope")
-                refreshed_url = _optional_base_url(refreshed.get("inference_base_url"))
-                if refreshed_url:
-                    inference_base_url = refreshed_url
-                state["obtained_at"] = now.isoformat()
-                state["expires_in"] = access_ttl
-                state["expires_at"] = datetime.fromtimestamp(
-                    now.timestamp() + access_ttl, tz=timezone.utc
-                ).isoformat()
-                access_token = state["access_token"]
-                refresh_token = state["refresh_token"]
-                _oauth_trace(
-                    "refresh_success",
-                    sequence_id=sequence_id,
-                    reason="access_expiring",
-                    previous_refresh_token_fp=_token_fingerprint(previous_refresh_token),
-                    new_refresh_token_fp=_token_fingerprint(refresh_token),
-                )
-                # Persist immediately so downstream mint failures cannot drop rotated refresh tokens.
-                _persist_state("post_refresh_access_expiring")
+                    if _is_expiring(state.get("expires_at"), ACCESS_TOKEN_REFRESH_SKEW_SECONDS):
+                        if not isinstance(refresh_token, str) or not refresh_token:
+                            raise AuthError("Session expired and no refresh token is available.",
+                                            provider="nous", relogin_required=True)
+
+                        _oauth_trace(
+                            "refresh_start",
+                            sequence_id=sequence_id,
+                            reason="access_expiring",
+                            refresh_token_fp=_token_fingerprint(refresh_token),
+                        )
+                        refreshed = _refresh_access_token(
+                            client=client, portal_base_url=portal_base_url,
+                            client_id=client_id, refresh_token=refresh_token,
+                        )
+                        now = datetime.now(timezone.utc)
+                        access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
+                        previous_refresh_token = refresh_token
+                        state["access_token"] = refreshed["access_token"]
+                        state["refresh_token"] = refreshed.get("refresh_token") or refresh_token
+                        state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
+                        state["scope"] = refreshed.get("scope") or state.get("scope")
+                        refreshed_url = _optional_base_url(refreshed.get("inference_base_url"))
+                        if refreshed_url:
+                            inference_base_url = refreshed_url
+                        state["obtained_at"] = now.isoformat()
+                        state["expires_in"] = access_ttl
+                        state["expires_at"] = datetime.fromtimestamp(
+                            now.timestamp() + access_ttl, tz=timezone.utc
+                        ).isoformat()
+                        access_token = state["access_token"]
+                        refresh_token = state["refresh_token"]
+                        _oauth_trace(
+                            "refresh_success",
+                            sequence_id=sequence_id,
+                            reason="access_expiring",
+                            previous_refresh_token_fp=_token_fingerprint(previous_refresh_token),
+                            new_refresh_token_fp=_token_fingerprint(refresh_token),
+                        )
+                        # Persist immediately so downstream mint failures cannot drop rotated refresh tokens.
+                        _persist_state("post_refresh_access_expiring")
 
             # Step 2: mint agent key if missing/expiring
             used_cached_key = False
@@ -3410,41 +3695,47 @@ def resolve_nous_runtime_credentials(
                         and isinstance(latest_refresh_token, str)
                         and latest_refresh_token
                     ):
-                        _oauth_trace(
-                            "refresh_start",
-                            sequence_id=sequence_id,
-                            reason="mint_retry_after_invalid_token",
-                            refresh_token_fp=_token_fingerprint(latest_refresh_token),
-                        )
-                        refreshed = _refresh_access_token(
-                            client=client, portal_base_url=portal_base_url,
-                            client_id=client_id, refresh_token=latest_refresh_token,
-                        )
-                        now = datetime.now(timezone.utc)
-                        access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
-                        state["access_token"] = refreshed["access_token"]
-                        state["refresh_token"] = refreshed.get("refresh_token") or latest_refresh_token
-                        state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
-                        state["scope"] = refreshed.get("scope") or state.get("scope")
-                        refreshed_url = _optional_base_url(refreshed.get("inference_base_url"))
-                        if refreshed_url:
-                            inference_base_url = refreshed_url
-                        state["obtained_at"] = now.isoformat()
-                        state["expires_in"] = access_ttl
-                        state["expires_at"] = datetime.fromtimestamp(
-                            now.timestamp() + access_ttl, tz=timezone.utc
-                        ).isoformat()
-                        access_token = state["access_token"]
-                        refresh_token = state["refresh_token"]
-                        _oauth_trace(
-                            "refresh_success",
-                            sequence_id=sequence_id,
-                            reason="mint_retry_after_invalid_token",
-                            previous_refresh_token_fp=_token_fingerprint(latest_refresh_token),
-                            new_refresh_token_fp=_token_fingerprint(refresh_token),
-                        )
-                        # Persist retry refresh immediately for crash safety and cross-process visibility.
-                        _persist_state("post_refresh_mint_retry")
+                        with _nous_shared_store_lock(timeout_seconds=max(timeout_seconds + 5.0, AUTH_LOCK_TIMEOUT_SECONDS)):
+                            if _merge_shared_nous_oauth_state(state):
+                                access_token = state.get("access_token")
+                                latest_refresh_token = state.get("refresh_token")
+                                _persist_state("post_shared_merge_mint_retry")
+                            else:
+                                _oauth_trace(
+                                    "refresh_start",
+                                    sequence_id=sequence_id,
+                                    reason="mint_retry_after_invalid_token",
+                                    refresh_token_fp=_token_fingerprint(latest_refresh_token),
+                                )
+                                refreshed = _refresh_access_token(
+                                    client=client, portal_base_url=portal_base_url,
+                                    client_id=client_id, refresh_token=latest_refresh_token,
+                                )
+                                now = datetime.now(timezone.utc)
+                                access_ttl = _coerce_ttl_seconds(refreshed.get("expires_in"))
+                                state["access_token"] = refreshed["access_token"]
+                                state["refresh_token"] = refreshed.get("refresh_token") or latest_refresh_token
+                                state["token_type"] = refreshed.get("token_type") or state.get("token_type") or "Bearer"
+                                state["scope"] = refreshed.get("scope") or state.get("scope")
+                                refreshed_url = _optional_base_url(refreshed.get("inference_base_url"))
+                                if refreshed_url:
+                                    inference_base_url = refreshed_url
+                                state["obtained_at"] = now.isoformat()
+                                state["expires_in"] = access_ttl
+                                state["expires_at"] = datetime.fromtimestamp(
+                                    now.timestamp() + access_ttl, tz=timezone.utc
+                                ).isoformat()
+                                access_token = state["access_token"]
+                                refresh_token = state["refresh_token"]
+                                _oauth_trace(
+                                    "refresh_success",
+                                    sequence_id=sequence_id,
+                                    reason="mint_retry_after_invalid_token",
+                                    previous_refresh_token_fp=_token_fingerprint(latest_refresh_token),
+                                    new_refresh_token_fp=_token_fingerprint(refresh_token),
+                                )
+                                # Persist retry refresh immediately for crash safety and cross-process visibility.
+                                _persist_state("post_refresh_mint_retry")
 
                         mint_payload = _mint_agent_key(
                             client=client, portal_base_url=portal_base_url,
@@ -3940,6 +4231,14 @@ def _config_provider_matches(provider_id: Optional[str]) -> bool:
     return _get_config_provider() == provider_id.strip().lower()
 
 
+def _should_reset_config_provider_on_logout(provider_id: Optional[str]) -> bool:
+    """Return True when logout should reset the model provider config."""
+    if not provider_id:
+        return False
+    normalized = provider_id.strip().lower()
+    return normalized in PROVIDER_REGISTRY and _config_provider_matches(normalized)
+
+
 def _logout_default_provider_from_config() -> Optional[str]:
     """Fallback logout target when auth.json has no active provider.
 
@@ -5025,15 +5324,18 @@ def logout_command(args) -> None:
         print("No provider is currently logged in.")
         return
 
-    config_matches = _config_provider_matches(target)
+    should_reset_config = _should_reset_config_provider_on_logout(target)
     provider_name = get_auth_provider_display_name(target)
 
-    if clear_provider_auth(target) or config_matches:
-        _reset_config_provider()
+    if clear_provider_auth(target) or should_reset_config:
+        if should_reset_config:
+            _reset_config_provider()
         print(f"Logged out of {provider_name}.")
-        if os.getenv("OPENROUTER_API_KEY"):
+        if should_reset_config and os.getenv("OPENROUTER_API_KEY"):
             print("Hermes will use OpenRouter for inference.")
-        else:
+        elif should_reset_config:
             print("Run `hermes model` or configure an API key to use Hermes.")
+        else:
+            print("Model provider configuration was unchanged.")
     else:
         print(f"No auth state found for {provider_name}.")

hermes_cli/commands.py

@@ -109,6 +109,9 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("resume", "Resume a previously-named session", "Session",
                args_hint="[name]"),
 
+    # Configuration
+    CommandDef("sessions", "Browse and resume previous sessions", "Session"),
+
     # Configuration
     CommandDef("config", "Show current configuration", "Configuration",
                cli_only=True),
@@ -157,9 +160,9 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
                cli_only=True, args_hint="[subcommand]",
                subcommands=("list", "add", "create", "edit", "pause", "resume", "run", "remove")),
-    CommandDef("curator", "Background skill maintenance (status, run, pin, archive)",
+    CommandDef("curator", "Background skill maintenance (status, run, pin, archive, list-archived)",
                "Tools & Skills", args_hint="[subcommand]",
-               subcommands=("status", "run", "pause", "resume", "pin", "unpin", "restore")),
+               subcommands=("status", "run", "pause", "resume", "pin", "unpin", "restore", "list-archived")),
     CommandDef("kanban", "Multi-profile collaboration board (tasks, links, comments)",
                "Tools & Skills", args_hint="[subcommand]",
                subcommands=("list", "ls", "show", "create", "assign", "link", "unlink",

hermes_cli/config.py

@@ -21,6 +21,7 @@ import stat
 import subprocess
 import sys
 import tempfile
+import threading
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Dict, Any, Optional, List, Tuple
@@ -42,6 +43,14 @@ _LOAD_CONFIG_CACHE: Dict[str, Tuple[int, int, Dict[str, Any]]] = {}
 # _LOAD_CONFIG_CACHE but for read_raw_config() — used when callers want
 # the user's on-disk values without defaults merged in.
 _RAW_CONFIG_CACHE: Dict[str, Tuple[int, int, Dict[str, Any]]] = {}
+# Serializes all config read/write paths. libyaml's C extension is not
+# thread-safe for concurrent safe_load() on the same file, and multiple
+# tool threads (approval.py, browser_tool.py, setup flows) hit
+# load_config / read_raw_config / save_config from different threads
+# during long agent runs. RLock (not Lock) because save_config internally
+# calls read_raw_config. Also covers mutation of the module-level cache
+# dicts above.
+_CONFIG_LOCK = threading.RLock()
 # Env var names written to .env that aren't in OPTIONAL_ENV_VARS
 # (managed by setup/provider flows directly).
 _EXTRA_ENV_KEYS = frozenset({
@@ -780,6 +789,19 @@ DEFAULT_CONFIG = {
             "timeout": 30,
             "extra_body": {},
         },
+        # Triage specifier — flesh out a rough one-liner in the Kanban
+        # Triage column into a concrete spec, then promote it to ``todo``.
+        # Invoked by ``hermes kanban specify`` (single id or --all). Set a
+        # cheap, capable model here (gemini-flash works well); the main
+        # model is overkill for short spec expansion.
+        "triage_specifier": {
+            "provider": "auto",
+            "model": "",
+            "base_url": "",
+            "api_key": "",
+            "timeout": 120,
+            "extra_body": {},
+        },
         # Curator — skill-usage review fork. Timeout is generous because the
         # review pass can take several minutes on reasoning models (umbrella
         # building over hundreds of candidate skills). "auto" = use main chat
@@ -1106,6 +1128,14 @@ DEFAULT_CONFIG = {
     # Empty string means use server-local time.
     "timezone": "",
 
+    # Slack platform settings (gateway mode)
+    "slack": {
+        "require_mention": True,       # Require @mention to respond in channels
+        "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
+        "allowed_channels": "",        # If set, bot ONLY responds in these channel IDs (whitelist)
+        "channel_prompts": {},         # Per-channel ephemeral system prompts
+    },
+
     # Discord platform settings (gateway mode)
     "discord": {
         "require_mention": True,       # Require @mention to respond in server channels
@@ -1114,6 +1144,12 @@ DEFAULT_CONFIG = {
         "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
         "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
         "channel_prompts": {},         # Per-channel ephemeral system prompts (forum parents apply to child threads)
+        # Opt-in DM role-based auth (#12136). By default, DISCORD_ALLOWED_ROLES
+        # authorizes only guild messages in the role's own guild — DMs require
+        # DISCORD_ALLOWED_USERS. Set dm_role_auth_guild to a guild ID to also
+        # authorize DMs from members of that one trusted guild holding the
+        # allowed role. Unset / empty / 0 = secure default (DM role-auth off).
+        "dm_role_auth_guild": "",
         # discord / discord_admin tools: restrict which actions the agent may call.
         # Default (empty) = all actions allowed (subject to bot privileged intents).
         # Accepts comma-separated string ("list_guilds,list_channels,fetch_messages")
@@ -1136,18 +1172,24 @@ DEFAULT_CONFIG = {
     "telegram": {
         "reactions": False,            # Add 👀/✅/❌ reactions to messages during processing
         "channel_prompts": {},         # Per-chat/topic ephemeral system prompts (topics inherit from parent group)
-    },
-
-    # Slack platform settings (gateway mode)
-    "slack": {
-        "channel_prompts": {},         # Per-channel ephemeral system prompts
+        "allowed_chats": "",           # If set, bot ONLY responds in these group/supergroup chat IDs (whitelist)
     },
 
     # Mattermost platform settings (gateway mode)
     "mattermost": {
+        "require_mention": True,       # Require @mention to respond in channels
+        "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
+        "allowed_channels": "",        # If set, bot ONLY responds in these channel IDs (whitelist)
         "channel_prompts": {},         # Per-channel ephemeral system prompts
     },
 
+    # Matrix platform settings (gateway mode)
+    "matrix": {
+        "require_mention": True,       # Require @mention to respond in rooms
+        "free_response_rooms": "",     # Comma-separated room IDs where bot responds without mention
+        "allowed_rooms": "",           # If set, bot ONLY responds in these room IDs (whitelist)
+    },
+
     # Approval mode for dangerous commands:
     #   manual — always prompt the user (default)
     #   smart  — use auxiliary LLM to auto-approve low-risk commands, prompt for high-risk
@@ -1197,7 +1239,7 @@ DEFAULT_CONFIG = {
     # Pre-exec security scanning via tirith
     "security": {
         "allow_private_urls": False,  # Allow requests to private/internal IPs (for OpenWrt, proxies, VPNs)
-        "redact_secrets": False,
+        "redact_secrets": True,
         "tirith_enabled": True,
         "tirith_path": "tirith",
         "tirith_timeout": 5,
@@ -1236,6 +1278,10 @@ DEFAULT_CONFIG = {
         # Seconds between dispatcher ticks (idle or not). Lower = snappier
         # pickup of newly-ready tasks; higher = less SQL pressure.
         "dispatch_interval_seconds": 60,
+        # Auto-block after this many consecutive non-success attempts for the
+        # same task/profile (spawn_failed, timed_out, or crashed). Reassignment
+        # resets the streak for the new profile.
+        "failure_limit": 2,
     },
 
     # execute_code settings — controls the tool used for programmatic tool calls.
@@ -1846,6 +1892,14 @@ OPTIONAL_ENV_VARS = {
         "password": False,
         "category": "tool",
     },
+    "BRAVE_SEARCH_API_KEY": {
+        "description": "Brave Search API subscription token (free tier: 2,000 queries/mo)",
+        "prompt": "Brave Search subscription token",
+        "url": "https://brave.com/search/api/",
+        "tools": ["web_search"],
+        "password": True,
+        "category": "tool",
+    },
     "BROWSERBASE_API_KEY": {
         "description": "Browserbase API key for cloud browser (optional — local browser works without this)",
         "prompt": "Browserbase API key",
@@ -3903,28 +3957,29 @@ def read_raw_config() -> Dict[str, Any]:
     ``load_config()``. Returns a deepcopy on every call since some callers
     mutate the result before passing to ``save_config()``.
     """
-    try:
-        config_path = get_config_path()
-        st = config_path.stat()
-        cache_key = (st.st_mtime_ns, st.st_size)
-    except (FileNotFoundError, OSError):
-        return {}
+    with _CONFIG_LOCK:
+        try:
+            config_path = get_config_path()
+            st = config_path.stat()
+            cache_key = (st.st_mtime_ns, st.st_size)
+        except (FileNotFoundError, OSError):
+            return {}
 
-    path_key = str(config_path)
-    cached = _RAW_CONFIG_CACHE.get(path_key)
-    if cached is not None and cached[:2] == cache_key:
-        return copy.deepcopy(cached[2])
+        path_key = str(config_path)
+        cached = _RAW_CONFIG_CACHE.get(path_key)
+        if cached is not None and cached[:2] == cache_key:
+            return copy.deepcopy(cached[2])
 
-    try:
-        with open(config_path, encoding="utf-8") as f:
-            data = yaml.safe_load(f) or {}
-    except Exception:
-        return {}
+        try:
+            with open(config_path, encoding="utf-8") as f:
+                data = yaml.safe_load(f) or {}
+        except Exception:
+            return {}
 
-    if not isinstance(data, dict):
-        data = {}
-    _RAW_CONFIG_CACHE[path_key] = (cache_key[0], cache_key[1], copy.deepcopy(data))
-    return data
+        if not isinstance(data, dict):
+            data = {}
+        _RAW_CONFIG_CACHE[path_key] = (cache_key[0], cache_key[1], copy.deepcopy(data))
+        return data
 
 
 def load_config() -> Dict[str, Any]:
@@ -3937,54 +3992,55 @@ def load_config() -> Dict[str, Any]:
     (which change ``HERMES_HOME`` and therefore ``get_config_path()``)
     don't collide.
     """
-    ensure_hermes_home()
-    config_path = get_config_path()
-    path_key = str(config_path)
+    with _CONFIG_LOCK:
+        ensure_hermes_home()
+        config_path = get_config_path()
+        path_key = str(config_path)
 
-    try:
-        st = config_path.stat()
-        cache_key: Optional[Tuple[int, int]] = (st.st_mtime_ns, st.st_size)
-    except FileNotFoundError:
-        cache_key = None
-
-    cached = _LOAD_CONFIG_CACHE.get(path_key)
-    if cached is not None and cache_key is not None and cached[:2] == cache_key:
-        return copy.deepcopy(cached[2])
-
-    config = copy.deepcopy(DEFAULT_CONFIG)
-
-    if cache_key is not None:
         try:
-            with open(config_path, encoding="utf-8") as f:
-                user_config = yaml.safe_load(f) or {}
+            st = config_path.stat()
+            cache_key: Optional[Tuple[int, int]] = (st.st_mtime_ns, st.st_size)
+        except FileNotFoundError:
+            cache_key = None
 
-            if "max_turns" in user_config:
-                agent_user_config = dict(user_config.get("agent") or {})
-                if agent_user_config.get("max_turns") is None:
-                    agent_user_config["max_turns"] = user_config["max_turns"]
-                user_config["agent"] = agent_user_config
-                user_config.pop("max_turns", None)
+        cached = _LOAD_CONFIG_CACHE.get(path_key)
+        if cached is not None and cache_key is not None and cached[:2] == cache_key:
+            return copy.deepcopy(cached[2])
 
-            config = _deep_merge(config, user_config)
-        except Exception as e:
-            print(f"Warning: Failed to load config: {e}")
+        config = copy.deepcopy(DEFAULT_CONFIG)
 
-    normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
-    expanded = _expand_env_vars(normalized)
-    _LAST_EXPANDED_CONFIG_BY_PATH[path_key] = copy.deepcopy(expanded)
-    if cache_key is not None:
-        _LOAD_CONFIG_CACHE[path_key] = (cache_key[0], cache_key[1], copy.deepcopy(expanded))
-    else:
-        _LOAD_CONFIG_CACHE.pop(path_key, None)
-    return expanded
+        if cache_key is not None:
+            try:
+                with open(config_path, encoding="utf-8") as f:
+                    user_config = yaml.safe_load(f) or {}
+
+                if "max_turns" in user_config:
+                    agent_user_config = dict(user_config.get("agent") or {})
+                    if agent_user_config.get("max_turns") is None:
+                        agent_user_config["max_turns"] = user_config["max_turns"]
+                    user_config["agent"] = agent_user_config
+                    user_config.pop("max_turns", None)
+
+                config = _deep_merge(config, user_config)
+            except Exception as e:
+                print(f"Warning: Failed to load config: {e}")
+
+        normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
+        expanded = _expand_env_vars(normalized)
+        _LAST_EXPANDED_CONFIG_BY_PATH[path_key] = copy.deepcopy(expanded)
+        if cache_key is not None:
+            _LOAD_CONFIG_CACHE[path_key] = (cache_key[0], cache_key[1], copy.deepcopy(expanded))
+        else:
+            _LOAD_CONFIG_CACHE.pop(path_key, None)
+        return expanded
 
 
 _SECURITY_COMMENT = """
 # ── Security ──────────────────────────────────────────────────────────
-# Secret redaction is OFF by default — tool output (terminal stdout,
-# read_file results, web content) passes through unmodified. Set
-# redact_secrets to true to mask strings that look like API keys, tokens,
-# and passwords before they enter the model context and logs.
+# Secret redaction is ON by default — strings that look like API keys,
+# tokens, and passwords are masked in tool output, logs, and chat
+# responses before the model or user ever sees them. Set redact_secrets
+# to false to disable (e.g. when developing the redactor itself).
 # tirith pre-exec scanning is enabled by default when the tirith binary
 # is available. Configure via security.tirith_* keys or env vars
 # (TIRITH_ENABLED, TIRITH_BIN, TIRITH_TIMEOUT, TIRITH_FAIL_OPEN).
@@ -4024,8 +4080,8 @@ _FALLBACK_COMMENT = """
 
 _COMMENTED_SECTIONS = """
 # ── Security ──────────────────────────────────────────────────────────
-# Secret redaction is OFF by default. Set to true to mask strings that
-# look like API keys, tokens, and passwords in tool output and logs.
+# Secret redaction is ON by default. Set to false to pass tool output,
+# logs, and chat responses through unmodified (e.g. for redactor dev).
 #
 # security:
 #   redact_secrets: true
@@ -4056,45 +4112,46 @@ _COMMENTED_SECTIONS = """
 
 def save_config(config: Dict[str, Any]):
     """Save configuration to ~/.hermes/config.yaml."""
-    if is_managed():
-        managed_error("save configuration")
-        return
-    from utils import atomic_yaml_write
+    with _CONFIG_LOCK:
+        if is_managed():
+            managed_error("save configuration")
+            return
+        from utils import atomic_yaml_write
 
-    ensure_hermes_home()
-    config_path = get_config_path()
-    current_normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
-    normalized = current_normalized
-    raw_existing = _normalize_root_model_keys(_normalize_max_turns_config(read_raw_config()))
-    if raw_existing:
-        normalized = _preserve_env_ref_templates(
+        ensure_hermes_home()
+        config_path = get_config_path()
+        current_normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
+        normalized = current_normalized
+        raw_existing = _normalize_root_model_keys(_normalize_max_turns_config(read_raw_config()))
+        if raw_existing:
+            normalized = _preserve_env_ref_templates(
+                normalized,
+                raw_existing,
+                _LAST_EXPANDED_CONFIG_BY_PATH.get(str(config_path)),
+            )
+
+        # Build optional commented-out sections for features that are off by
+        # default or only relevant when explicitly configured.
+        parts = []
+        sec = normalized.get("security", {})
+        if not sec or sec.get("redact_secrets") is None:
+            parts.append(_SECURITY_COMMENT)
+        fb = normalized.get("fallback_model", {})
+        fb_is_valid = False
+        if isinstance(fb, list):
+            fb_is_valid = any(isinstance(e, dict) and e.get("provider") and e.get("model") for e in fb)
+        elif isinstance(fb, dict):
+            fb_is_valid = bool(fb.get("provider") and fb.get("model"))
+        if not fb_is_valid:
+            parts.append(_FALLBACK_COMMENT)
+
+        atomic_yaml_write(
+            config_path,
             normalized,
-            raw_existing,
-            _LAST_EXPANDED_CONFIG_BY_PATH.get(str(config_path)),
+            extra_content="".join(parts) if parts else None,
         )
-
-    # Build optional commented-out sections for features that are off by
-    # default or only relevant when explicitly configured.
-    parts = []
-    sec = normalized.get("security", {})
-    if not sec or sec.get("redact_secrets") is None:
-        parts.append(_SECURITY_COMMENT)
-    fb = normalized.get("fallback_model", {})
-    fb_is_valid = False
-    if isinstance(fb, list):
-        fb_is_valid = any(isinstance(e, dict) and e.get("provider") and e.get("model") for e in fb)
-    elif isinstance(fb, dict):
-        fb_is_valid = bool(fb.get("provider") and fb.get("model"))
-    if not fb_is_valid:
-        parts.append(_FALLBACK_COMMENT)
-
-    atomic_yaml_write(
-        config_path,
-        normalized,
-        extra_content="".join(parts) if parts else None,
-    )
-    _secure_file(config_path)
-    _LAST_EXPANDED_CONFIG_BY_PATH[str(config_path)] = copy.deepcopy(current_normalized)
+        _secure_file(config_path)
+        _LAST_EXPANDED_CONFIG_BY_PATH[str(config_path)] = copy.deepcopy(current_normalized)
 
 
 def load_env() -> Dict[str, str]:
@@ -4944,3 +5001,100 @@ def _inject_profile_env_vars() -> None:
 
 # Eagerly inject so that OPTIONAL_ENV_VARS is fully populated at import time.
 _inject_profile_env_vars()
+
+
+# ── Platform-plugin env var injection ────────────────────────────────────────
+# Bundled platform plugins under ``plugins/platforms/*/plugin.yaml`` declare
+# their required env vars via ``requires_env``.  This mirror of
+# ``_inject_profile_env_vars`` surfaces them in ``hermes config`` UI so users
+# can configure Teams / IRC / Google Chat without the core repo ever needing
+# to know they exist.
+#
+# Each ``requires_env`` entry may be a bare string (name only) or a dict:
+#
+#   requires_env:
+#     - TEAMS_CLIENT_ID                          # minimal
+#     - name: TEAMS_CLIENT_SECRET                # rich
+#       description: "Teams bot client secret"
+#       url: "https://portal.azure.com/"
+#       password: true
+#       prompt: "Teams client secret"
+#
+# An optional ``optional_env`` block surfaces non-required vars the same way
+# (e.g. allowlist, home channel).
+
+_platform_plugin_env_vars_injected = False
+
+
+def _inject_platform_plugin_env_vars() -> None:
+    """Populate OPTIONAL_ENV_VARS from bundled platform plugin manifests.
+
+    Called once at module load time. Idempotent — repeated calls are no-ops.
+    Failures are swallowed so a malformed plugin.yaml can't break CLI import.
+    """
+    global _platform_plugin_env_vars_injected
+    if _platform_plugin_env_vars_injected:
+        return
+    _platform_plugin_env_vars_injected = True
+    try:
+        import yaml  # type: ignore
+
+        # Resolve the bundled plugins dir from this file's location so the
+        # injector works regardless of CWD.
+        repo_root = Path(__file__).resolve().parents[1]
+        platforms_dir = repo_root / "plugins" / "platforms"
+        if not platforms_dir.is_dir():
+            return
+        for child in platforms_dir.iterdir():
+            if not child.is_dir():
+                continue
+            manifest_path = child / "plugin.yaml"
+            if not manifest_path.exists():
+                manifest_path = child / "plugin.yml"
+            if not manifest_path.exists():
+                continue
+            try:
+                with open(manifest_path, "r", encoding="utf-8") as f:
+                    manifest = yaml.safe_load(f) or {}
+            except Exception:
+                continue
+            label = manifest.get("label") or manifest.get("name") or child.name
+            # Merge required + optional env var declarations.
+            entries = list(manifest.get("requires_env") or [])
+            entries.extend(manifest.get("optional_env") or [])
+            for entry in entries:
+                if isinstance(entry, str):
+                    name = entry
+                    meta: dict = {}
+                elif isinstance(entry, dict) and entry.get("name"):
+                    name = entry["name"]
+                    meta = entry
+                else:
+                    continue
+                if name in OPTIONAL_ENV_VARS:
+                    continue  # hardcoded entry wins (back-compat)
+                # Heuristic: anything named *TOKEN, *SECRET, *KEY, *PASSWORD
+                # is a password field unless explicitly overridden.
+                name_upper = name.upper()
+                is_secret = bool(meta.get("password") or meta.get("secret"))
+                if not is_secret and not meta.get("password") is False:
+                    is_secret = any(
+                        name_upper.endswith(suf)
+                        for suf in ("_TOKEN", "_SECRET", "_KEY", "_PASSWORD", "_JSON")
+                    )
+                OPTIONAL_ENV_VARS[name] = {
+                    "description": (
+                        meta.get("description")
+                        or f"{label} configuration"
+                    ),
+                    "prompt": meta.get("prompt") or name,
+                    "url": meta.get("url") or None,
+                    "password": is_secret,
+                    "category": meta.get("category") or "messaging",
+                }
+    except Exception:
+        pass
+
+
+# Eagerly inject so that platform plugin env vars show up in the setup wizard.
+_inject_platform_plugin_env_vars()

hermes_cli/copilot_auth.py

@@ -212,9 +212,9 @@ def copilot_device_code_login(
     print("  Waiting for authorization...", end="", flush=True)
 
     # Step 3: Poll for completion
-    deadline = time.time() + timeout_seconds
+    deadline = time.monotonic() + timeout_seconds
 
-    while time.time() < deadline:
+    while time.monotonic() < deadline:
         time.sleep(interval + _DEVICE_CODE_POLL_SAFETY_MARGIN)
 
         poll_data = urllib.parse.urlencode({

hermes_cli/curator.py

@@ -12,6 +12,7 @@ from __future__ import annotations
 import argparse
 import sys
 from datetime import datetime, timezone
+from pathlib import Path
 from typing import Optional
 
 
@@ -57,7 +58,8 @@ def _cmd_status(args) -> int:
     print(f"  last summary:   {summary}")
     _report = state.get("last_report_path")
     if _report:
-        print(f"  last report:    {_report}")
+        suffix = "" if Path(_report).exists() else " (missing)"
+        print(f"  last report:    {_report}{suffix}")
     _ih = curator.get_interval_hours()
     _interval_label = (
         f"{_ih // 24}d" if _ih % 24 == 0 and _ih >= 24
@@ -161,6 +163,8 @@ def _cmd_run(args) -> int:
         return 1
 
     dry = bool(getattr(args, "dry_run", False))
+    background = bool(getattr(args, "background", False))
+    synchronous = bool(getattr(args, "synchronous", False)) or not background
     if dry:
         print("curator: running DRY-RUN (report only, no mutations)...")
     else:
@@ -171,7 +175,7 @@ def _cmd_run(args) -> int:
 
     result = curator.run_curator_review(
         on_summary=_on_summary,
-        synchronous=bool(args.synchronous),
+        synchronous=synchronous,
         dry_run=dry,
     )
     auto = result.get("auto_transitions", {})
@@ -188,13 +192,19 @@ def _cmd_run(args) -> int:
                 f"archived={auto.get('archived', 0)} "
                 f"reactivated={auto.get('reactivated', 0)}"
             )
-    if not args.synchronous:
+    if not synchronous:
         print("llm pass running in background — check `hermes curator status` later")
     if dry:
-        print(
-            "dry-run: no changes applied. When the report lands, read it with "
-            "`hermes curator status` and run `hermes curator run` (no flag) to apply."
-        )
+        if synchronous:
+            print(
+                "dry-run: no changes applied. Read the report with "
+                "`hermes curator status` and run `hermes curator run` (no flag) to apply."
+            )
+        else:
+            print(
+                "dry-run: no changes applied. When the report lands, read it with "
+                "`hermes curator status` and run `hermes curator run` (no flag) to apply."
+            )
     return 0
 
 
@@ -442,6 +452,18 @@ def _cmd_rollback(args) -> int:
     return 1
 
 
+def _cmd_list_archived(args) -> int:
+    """List archived (recoverable) skills."""
+    from tools import skill_usage
+    names = skill_usage.list_archived_skill_names()
+    if not names:
+        print("curator: no archived skills")
+        return 0
+    for name in names:
+        print(name)
+    return 0
+
+
 # ---------------------------------------------------------------------------
 # argparse wiring (called from hermes_cli.main)
 # ---------------------------------------------------------------------------
@@ -461,7 +483,11 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
     p_run = subs.add_parser("run", help="Trigger a curator review now")
     p_run.add_argument(
         "--sync", "--synchronous", dest="synchronous", action="store_true",
-        help="Wait for the LLM review pass to finish (default: background thread)",
+        help="Wait for the LLM review pass to finish (default for manual runs)",
+    )
+    p_run.add_argument(
+        "--background", dest="background", action="store_true",
+        help="Start the LLM review pass in a background thread and return immediately",
     )
     p_run.add_argument(
         "--dry-run", dest="dry_run", action="store_true",
@@ -488,6 +514,9 @@ def register_cli(parent: argparse.ArgumentParser) -> None:
     p_restore.add_argument("skill", help="Skill name")
     p_restore.set_defaults(func=_cmd_restore)
 
+    subs.add_parser("list-archived", help="List archived skills") \
+        .set_defaults(func=_cmd_list_archived)
+
     p_archive = subs.add_parser(
         "archive",
         help="Manually archive a skill (move to .archive/, excluded from prompt)",

hermes_cli/doctor.py

@@ -91,6 +91,15 @@ def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
     return steps
 
 
+def _termux_install_all_fallback_notes() -> list[str]:
+    return [
+        "Termux install profile: use .[termux-all] for broad compatibility (installer default on Termux).",
+        "Matrix E2EE extra is excluded on Termux (python-olm currently fails to build).",
+        "Local faster-whisper extra is excluded on Termux (ctranslate2/av build path unavailable).",
+        "STT fallback: use Groq Whisper (set GROQ_API_KEY) or OpenAI Whisper (set VOICE_TOOLS_OPENAI_KEY).",
+    ]
+
+
 def _has_provider_env_config(content: str) -> bool:
     """Return True when ~/.hermes/.env contains provider auth/base URL settings."""
     return any(key in content for key in _PROVIDER_ENV_HINTS)
@@ -1084,6 +1093,11 @@ def run_doctor(args):
             except Exception:
                 pass
 
+    if _is_termux():
+        check_info("Termux compatibility fallbacks:")
+        for note in _termux_install_all_fallback_notes():
+            check_info(note)
+
     # =========================================================================
     # Check: API connectivity
     # =========================================================================
@@ -1225,6 +1239,16 @@ def run_doctor(args):
                     headers=_headers,
                     timeout=10,
                 )
+                if (
+                    _pname == "Alibaba/DashScope"
+                    and not _base
+                    and _resp.status_code == 401
+                ):
+                    _resp = httpx.get(
+                        "https://dashscope.aliyuncs.com/compatible-mode/v1/models",
+                        headers=_headers,
+                        timeout=10,
+                    )
                 if _resp.status_code == 200:
                     print(f"\r  {color('✓', Colors.GREEN)} {_label}                          ")
                 elif _resp.status_code == 401:

hermes_cli/gateway.py

@@ -505,6 +505,7 @@ def _read_systemd_unit_properties(
         "SubState",
         "Result",
         "ExecMainStatus",
+        "MainPID",
     ),
 ) -> dict[str, str]:
     """Return selected ``systemctl show`` properties for the gateway unit."""
@@ -538,6 +539,41 @@ def _read_systemd_unit_properties(
     return parsed
 
 
+def _systemd_main_pid_from_props(props: dict[str, str]) -> int | None:
+    try:
+        pid = int(props.get("MainPID", "0") or "0")
+    except (TypeError, ValueError):
+        return None
+    return pid if pid > 0 else None
+
+
+def _systemd_main_pid(system: bool = False) -> int | None:
+    return _systemd_main_pid_from_props(_read_systemd_unit_properties(system=system))
+
+
+def _read_gateway_runtime_status() -> dict | None:
+    try:
+        from gateway.status import read_runtime_status
+
+        state = read_runtime_status()
+    except Exception:
+        return None
+    return state if isinstance(state, dict) else None
+
+
+def _gateway_runtime_status_for_pid(pid: int | None) -> dict | None:
+    if not pid:
+        return None
+    state = _read_gateway_runtime_status()
+    if not state:
+        return None
+    try:
+        state_pid = int(state.get("pid", 0) or 0)
+    except (TypeError, ValueError):
+        return None
+    return state if state_pid == pid else None
+
+
 def _wait_for_systemd_service_restart(
     *,
     system: bool = False,
@@ -549,9 +585,10 @@ def _wait_for_systemd_service_restart(
 
     svc = get_service_name()
     scope_label = _service_scope_label(system).capitalize()
-    deadline = time.time() + timeout
+    deadline = time.monotonic() + timeout
+    printed_runtime_wait = False
 
-    while time.time() < deadline:
+    while time.monotonic() < deadline:
         props = _read_systemd_unit_properties(system=system)
         active_state = props.get("ActiveState", "")
         sub_state = props.get("SubState", "")
@@ -562,19 +599,32 @@ def _wait_for_systemd_service_restart(
             new_pid = get_running_pid()
         except Exception:
             new_pid = None
+        if not new_pid:
+            new_pid = _systemd_main_pid_from_props(props)
 
         if active_state == "active":
             if new_pid and (previous_pid is None or new_pid != previous_pid):
-                print(f"✓ {scope_label} service restarted (PID {new_pid})")
-                return True
-            if previous_pid is None:
-                print(f"✓ {scope_label} service restarted")
-                return True
+                runtime_state = _gateway_runtime_status_for_pid(new_pid)
+                gateway_state = (runtime_state or {}).get("gateway_state")
+                if gateway_state == "running":
+                    print(f"✓ {scope_label} service restarted (PID {new_pid})")
+                    return True
+                if gateway_state == "startup_failed":
+                    reason = (runtime_state or {}).get("exit_reason") or "startup failed"
+                    print(f"⚠ {scope_label} service process restarted (PID {new_pid}), but gateway startup failed: {reason}")
+                    return False
+                if not printed_runtime_wait:
+                    print(f"⏳ {scope_label} service process started (PID {new_pid}); waiting for gateway runtime...")
+                    printed_runtime_wait = True
 
         if active_state == "activating" and sub_state == "auto-restart":
             time.sleep(1)
             continue
 
+        if _systemd_unit_is_start_limited(props):
+            _print_systemd_start_limit_wait(system=system)
+            return False
+
         time.sleep(2)
 
     print(
@@ -585,6 +635,46 @@ def _wait_for_systemd_service_restart(
     return False
 
 
+def _systemd_unit_is_start_limited(props: dict[str, str]) -> bool:
+    result = props.get("Result", "").lower()
+    sub_state = props.get("SubState", "").lower()
+    return result == "start-limit-hit" or sub_state == "start-limit-hit"
+
+
+def _systemd_error_indicates_start_limit(exc: subprocess.CalledProcessError) -> bool:
+    parts: list[str] = []
+    for attr in ("stderr", "stdout", "output"):
+        value = getattr(exc, attr, None)
+        if not value:
+            continue
+        if isinstance(value, bytes):
+            value = value.decode(errors="replace")
+        parts.append(str(value))
+    text = "\n".join(parts).lower()
+    return (
+        "start-limit-hit" in text
+        or "start request repeated too quickly" in text
+        or "start-limit" in text
+    )
+
+
+def _systemd_service_is_start_limited(system: bool = False) -> bool:
+    return _systemd_unit_is_start_limited(_read_systemd_unit_properties(system=system))
+
+
+def _print_systemd_start_limit_wait(system: bool = False) -> None:
+    svc = get_service_name()
+    scope_label = _service_scope_label(system).capitalize()
+    scope_flag = " --system" if system else ""
+    systemctl_prefix = "systemctl " if system else "systemctl --user "
+    journal_prefix = "journalctl " if system else "journalctl --user "
+    print(f"⏳ {scope_label} service is temporarily rate-limited by systemd.")
+    print("  systemd is refusing another immediate start after repeated exits.")
+    print(f"  Wait for the start-limit window to expire, then run: {'sudo ' if system else ''}hermes gateway restart{scope_flag}")
+    print(f"  Or clear the failed state manually: {systemctl_prefix}reset-failed {svc}")
+    print(f"  Check logs: {journal_prefix}-u {svc} -l --since '5 min ago'")
+
+
 def _recover_pending_systemd_restart(system: bool = False, previous_pid: int | None = None) -> bool:
     """Recover a planned service restart that is stuck in systemd state."""
     props = _read_systemd_unit_properties(system=system)
@@ -740,6 +830,46 @@ def _print_other_profiles_gateway_status() -> None:
         pass
 
 
+def _gateway_list() -> None:
+    """List all profiles and their gateway running status.
+
+    Provides a single-command overview of every known profile and whether
+    its gateway is currently running, so multi-profile users don't have to
+    check each profile individually.
+    """
+    try:
+        from hermes_cli.profiles import list_profiles, get_active_profile_name
+    except Exception:
+        print("Unable to list profiles.")
+        return
+
+    profiles = list_profiles()
+    if not profiles:
+        print("No profiles found.")
+        return
+
+    current = get_active_profile_name()
+
+    print("Gateways:")
+    for prof in profiles:
+        marker = "✓" if prof.gateway_running else "✗"
+        label = prof.name
+        if prof.name == current:
+            label += " (current)"
+        parts = [f"  {marker} {label:<24s}"]
+        if prof.gateway_running:
+            try:
+                from gateway.status import get_running_pid
+                pid = get_running_pid(prof.path / "gateway.pid", cleanup_stale=False)
+                if pid:
+                    parts.append(f"PID {pid}")
+            except Exception:
+                pass
+        else:
+            parts.append("not running")
+        print(" — ".join(parts))
+
+
 def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None,
                            all_profiles: bool = False) -> int:
     """Kill any running gateway processes. Returns count killed.
@@ -967,6 +1097,27 @@ class UserSystemdUnavailableError(RuntimeError):
     """
 
 
+class SystemScopeRequiresRootError(RuntimeError):
+    """Raised when a system-scope gateway operation is attempted as non-root.
+
+    System-scope units live in ``/etc/systemd/system/`` and require root for
+    install / uninstall / start / stop / restart via ``systemctl``. The
+    previous behavior was ``sys.exit(1)`` which blew past the wizard's
+    ``except Exception`` guards and dumped the user at a bare shell prompt
+    with no guidance. Raising a typed exception lets callers that can
+    recover (the setup wizard) print actionable remediation instead, while
+    ``gateway_command`` still exits 1 with the same message for the direct
+    CLI path.
+
+    ``args[0]`` carries the user-facing message, ``args[1]`` the action name.
+    ``str(e)`` returns only the message (not the tuple repr) so format
+    strings like ``f"Failed: {e}"`` render cleanly.
+    """
+
+    def __str__(self) -> str:
+        return self.args[0] if self.args else ""
+
+
 def _user_dbus_socket_path() -> Path:
     """Return the expected per-user D-Bus socket path (regardless of existence)."""
     xdg = os.environ.get("XDG_RUNTIME_DIR") or f"/run/user/{os.getuid()}"
@@ -1382,8 +1533,10 @@ def print_systemd_scope_conflict_warning() -> None:
 
 def _require_root_for_system_service(action: str) -> None:
     if os.geteuid() != 0:
-        print(f"System gateway {action} requires root. Re-run with sudo.")
-        sys.exit(1)
+        raise SystemScopeRequiresRootError(
+            f"System gateway {action} requires root. Re-run with sudo.",
+            action,
+        )
 
 
 def _system_service_identity(run_as_user: str | None = None) -> tuple[str, str, str]:
@@ -1930,6 +2083,47 @@ def _select_systemd_scope(system: bool = False) -> bool:
     return get_systemd_unit_path(system=True).exists() and not get_systemd_unit_path(system=False).exists()
 
 
+def _system_scope_wizard_would_need_root(system: bool = False) -> bool:
+    """True when the setup wizard is about to trigger a system-scope operation
+    as a non-root user.
+
+    Replicates the decision ``_select_systemd_scope`` makes inside
+    ``systemd_start`` / ``systemd_restart`` / ``systemd_stop`` so the wizard
+    can detect the dead-end BEFORE prompting, rather than letting
+    ``SystemScopeRequiresRootError`` propagate out and leave the user
+    staring at a bare shell.
+    """
+    if os.geteuid() == 0:
+        return False
+    return _select_systemd_scope(system=system)
+
+
+def _print_system_scope_remediation(action: str) -> None:
+    """Print actionable remediation when the wizard skips a system-scope
+    prompt because the user isn't root. Keeps the wizard flowing instead of
+    aborting.
+    """
+    svc = get_service_name()
+    print_warning(
+        f"Gateway is installed as a system-wide service — "
+        f"{action} requires root."
+    )
+    print_info("  Options:")
+    print_info(f"    1. {action.capitalize()} it this time:")
+    if action == "start":
+        print_info(f"         sudo systemctl start {svc}")
+    elif action == "stop":
+        print_info(f"         sudo systemctl stop {svc}")
+    elif action == "restart":
+        print_info(f"         sudo systemctl restart {svc}")
+    else:
+        print_info(f"         sudo systemctl {action} {svc}")
+    print_info("    2. Switch to a per-user service (recommended for personal use):")
+    print_info("         sudo hermes gateway uninstall --system")
+    print_info("         hermes gateway install")
+    print_info("         hermes gateway start")
+
+
 def _get_restart_drain_timeout() -> float:
     """Return the configured gateway restart drain timeout in seconds."""
     raw = os.getenv("HERMES_RESTART_DRAIN_TIMEOUT", "").strip()
@@ -2071,41 +2265,52 @@ def systemd_restart(system: bool = False):
     refresh_systemd_unit_if_needed(system=system)
     from gateway.status import get_running_pid
 
-    pid = get_running_pid()
-    if pid is not None and _request_gateway_self_restart(pid):
-        import time
+    pid = get_running_pid() or _systemd_main_pid(system=system)
+    if pid is not None:
         scope_label = _service_scope_label(system).capitalize()
         svc = get_service_name()
+        drain_timeout = _get_restart_drain_timeout()
 
-        # Phase 1: wait for old process to exit (drain + shutdown)
-        print(f"⏳ {scope_label} service draining active work...")
-        deadline = time.time() + 90
-        while time.time() < deadline:
-            try:
-                os.kill(pid, 0)
-                time.sleep(1)
-            except (ProcessLookupError, PermissionError):
-                break  # old process is gone
-        else:
-            print(f"⚠ Old process (PID {pid}) still alive after 90s")
+        print(f"⏳ {scope_label} service restarting gracefully (PID {pid})...")
+        if _graceful_restart_via_sigusr1(pid, drain_timeout + 5):
+            # The gateway exits with code 75 for a planned service restart.
+            # RestartSec can otherwise delay the relaunch even though the
+            # operator asked for an immediate restart, so kick the unit once
+            # the old PID has exited and then wait for the replacement PID.
+            _run_systemctl(
+                ["reset-failed", svc],
+                system=system,
+                check=False,
+                timeout=30,
+            )
+            _run_systemctl(
+                ["restart", svc],
+                system=system,
+                check=False,
+                timeout=90,
+            )
+            if _wait_for_systemd_service_restart(system=system, previous_pid=pid):
+                return
+            if _systemd_service_is_start_limited(system=system):
+                return
 
-        # The gateway exits with code 75 for a planned service restart.
-        # systemd can sit in the RestartSec window or even wedge itself into a
-        # failed/rate-limited state if the operator asks for another restart in
-        # the middle of that handoff. Clear any stale failed state and kick the
-        # unit immediately so `hermes gateway restart` behaves idempotently.
+        print(
+            f"⚠ Graceful restart did not complete within {int(drain_timeout + 5)}s; "
+            "forcing a service restart..."
+        )
         _run_systemctl(
             ["reset-failed", svc],
             system=system,
             check=False,
             timeout=30,
         )
-        _run_systemctl(
-            ["start", svc],
-            system=system,
-            check=False,
-            timeout=90,
-        )
+        try:
+            _run_systemctl(["restart", svc], system=system, check=True, timeout=90)
+        except subprocess.CalledProcessError as exc:
+            if _systemd_error_indicates_start_limit(exc) or _systemd_service_is_start_limited(system=system):
+                _print_systemd_start_limit_wait(system=system)
+                return
+            raise
         _wait_for_systemd_service_restart(system=system, previous_pid=pid)
         return
 
@@ -2118,8 +2323,14 @@ def systemd_restart(system: bool = False):
         check=False,
         timeout=30,
     )
-    _run_systemctl(["reload-or-restart", get_service_name()], system=system, check=True, timeout=90)
-    print(f"✓ {_service_scope_label(system).capitalize()} service restarted")
+    try:
+        _run_systemctl(["restart", get_service_name()], system=system, check=True, timeout=90)
+    except subprocess.CalledProcessError as exc:
+        if _systemd_error_indicates_start_limit(exc) or _systemd_service_is_start_limited(system=system):
+            _print_systemd_start_limit_wait(system=system)
+            return
+        raise
+    _wait_for_systemd_service_restart(system=system, previous_pid=pid)
 
 
 
@@ -2191,6 +2402,10 @@ def systemd_status(deep: bool = False, system: bool = False, full: bool = False)
     result_code = unit_props.get("Result", "")
     if active_state == "activating" and sub_state == "auto-restart":
         print("  ⏳ Restart pending: systemd is waiting to relaunch the gateway")
+    elif _systemd_unit_is_start_limited(unit_props):
+        print("  ⏳ Restart pending: systemd is temporarily rate-limiting starts")
+        print(f"  Run after the start-limit window expires: {'sudo ' if system else ''}hermes gateway restart{scope_flag}")
+        print(f"  Or clear it manually: systemctl {'--user ' if not system else ''}reset-failed {get_service_name()}")
     elif active_state == "failed" and exec_main_status == str(GATEWAY_SERVICE_RESTART_EXIT_CODE):
         print("  ⚠ Planned restart is stuck in systemd failed state (exit 75)")
         print(f"  Run: systemctl {'--user ' if not system else ''}reset-failed {get_service_name()} && {'sudo ' if system else ''}hermes gateway start{scope_flag}")
@@ -2555,6 +2770,42 @@ def launchd_status(deep: bool = False):
 # Gateway Runner
 # =============================================================================
 
+def _truthy_env(value: str | None) -> bool:
+    return str(value or "").strip().lower() in {"1", "true", "yes", "on"}
+
+
+def _is_official_docker_checkout() -> bool:
+    return (
+        str(PROJECT_ROOT) == "/opt/hermes"
+        and (PROJECT_ROOT / "docker" / "entrypoint.sh").is_file()
+    )
+
+
+def _guard_official_docker_root_gateway() -> None:
+    """Refuse gateway startup when the official Docker privilege drop was bypassed."""
+    if not hasattr(os, "geteuid") or os.geteuid() != 0:
+        return
+    if _truthy_env(os.getenv("HERMES_ALLOW_ROOT_GATEWAY")):
+        return
+    if not _is_official_docker_checkout():
+        return
+
+    print_error(
+        "Refusing to run the Hermes gateway as root inside the official Docker image."
+    )
+    print(
+        "  The image entrypoint normally drops privileges to the 'hermes' user. "
+        "If you override entrypoint in Docker Compose, include "
+        "/opt/hermes/docker/entrypoint.sh before the Hermes command."
+    )
+    print(
+        "  Running the gateway as root can leave root-owned files in "
+        "$HERMES_HOME and break later non-root dashboard/gateway runs."
+    )
+    print("  Set HERMES_ALLOW_ROOT_GATEWAY=1 only if you intentionally accept this risk.")
+    sys.exit(1)
+
+
 def run_gateway(verbose: int = 0, quiet: bool = False, replace: bool = False):
     """Run the gateway in foreground.
     
@@ -2565,6 +2816,7 @@ def run_gateway(verbose: int = 0, quiet: bool = False, replace: bool = False):
                  This prevents systemd restart loops when the old process
                  hasn't fully exited yet.
     """
+    _guard_official_docker_root_gateway()
     sys.path.insert(0, str(PROJECT_ROOT))
 
     # Refresh the systemd unit definition on every boot so that restart
@@ -4115,7 +4367,9 @@ def gateway_setup():
         print_success("Gateway service is installed and running.")
     elif service_installed:
         print_warning("Gateway service is installed but not running.")
-        if prompt_yes_no("  Start it now?", True):
+        if supports_systemd_services() and _system_scope_wizard_would_need_root():
+            _print_system_scope_remediation("start")
+        elif prompt_yes_no("  Start it now?", True):
             try:
                 if supports_systemd_services():
                     systemd_start()
@@ -4125,6 +4379,12 @@ def gateway_setup():
                 print_error("  Failed to start — user systemd not reachable:")
                 for line in str(e).splitlines():
                     print(f"  {line}")
+            except SystemScopeRequiresRootError as e:
+                # Defense in depth: the pre-check above should have caught
+                # this, but handle the race/edge case gracefully instead of
+                # letting the exception escape the wizard.
+                print_error(f"  Failed to start: {e}")
+                _print_system_scope_remediation("start")
             except subprocess.CalledProcessError as e:
                 print_error(f"  Failed to start: {e}")
     else:
@@ -4174,7 +4434,9 @@ def gateway_setup():
         service_running = _is_service_running()
 
         if service_running:
-            if prompt_yes_no("  Restart the gateway to pick up changes?", True):
+            if supports_systemd_services() and _system_scope_wizard_would_need_root():
+                _print_system_scope_remediation("restart")
+            elif prompt_yes_no("  Restart the gateway to pick up changes?", True):
                 try:
                     if supports_systemd_services():
                         systemd_restart()
@@ -4187,10 +4449,15 @@ def gateway_setup():
                     print_error("  Restart failed — user systemd not reachable:")
                     for line in str(e).splitlines():
                         print(f"  {line}")
+                except SystemScopeRequiresRootError as e:
+                    print_error(f"  Restart failed: {e}")
+                    _print_system_scope_remediation("restart")
                 except subprocess.CalledProcessError as e:
                     print_error(f"  Restart failed: {e}")
         elif service_installed:
-            if prompt_yes_no("  Start the gateway service?", True):
+            if supports_systemd_services() and _system_scope_wizard_would_need_root():
+                _print_system_scope_remediation("start")
+            elif prompt_yes_no("  Start the gateway service?", True):
                 try:
                     if supports_systemd_services():
                         systemd_start()
@@ -4200,6 +4467,9 @@ def gateway_setup():
                     print_error("  Start failed — user systemd not reachable:")
                     for line in str(e).splitlines():
                         print(f"  {line}")
+                except SystemScopeRequiresRootError as e:
+                    print_error(f"  Start failed: {e}")
+                    _print_system_scope_remediation("start")
                 except subprocess.CalledProcessError as e:
                     print_error(f"  Start failed: {e}")
         else:
@@ -4273,6 +4543,14 @@ def gateway_command(args):
         for line in str(e).splitlines():
             print(f"  {line}")
         sys.exit(1)
+    except SystemScopeRequiresRootError as e:
+        # The direct ``hermes gateway install|uninstall|start|stop|restart``
+        # path lands here when the user typed a system-scope action without
+        # sudo. Same exit code as before — just gives the wizard a way to
+        # intercept the same condition with friendlier guidance before the
+        # error is raised.
+        print(str(e))
+        sys.exit(1)
 
 
 def _gateway_command_inner(args):
@@ -4597,6 +4875,9 @@ def _gateway_command_inner(args):
         # Show other profiles' gateway status for multi-profile awareness
         _print_other_profiles_gateway_status()
 
+    elif subcmd == "list":
+        _gateway_list()
+
     elif subcmd == "migrate-legacy":
         # Stop, disable, and remove legacy Hermes gateway unit files from
         # pre-rename installs (e.g. hermes.service). Profile units and

hermes_cli/goals.py

@@ -47,6 +47,14 @@ DEFAULT_MAX_TURNS = 20
 DEFAULT_JUDGE_TIMEOUT = 30.0
 # Cap how much of the last response + recent messages we send to the judge.
 _JUDGE_RESPONSE_SNIPPET_CHARS = 4000
+# After this many consecutive judge *parse* failures (empty output / non-JSON),
+# the loop auto-pauses and points the user at the goal_judge config. API /
+# transport errors do NOT count toward this — those are transient. This guards
+# against small models (e.g. deepseek-v4-flash) that cannot follow the strict
+# JSON reply contract; without it the loop runs until the turn budget is
+# exhausted with every reply shaped like `judge returned empty response` or
+# `judge reply was not JSON`.
+DEFAULT_MAX_CONSECUTIVE_PARSE_FAILURES = 3
 
 
 CONTINUATION_PROMPT_TEMPLATE = (
@@ -99,6 +107,7 @@ class GoalState:
     last_verdict: Optional[str] = None        # "done" | "continue" | "skipped"
     last_reason: Optional[str] = None
     paused_reason: Optional[str] = None       # why we auto-paused (budget, etc.)
+    consecutive_parse_failures: int = 0       # judge-output parse failures in a row
 
     def to_json(self) -> str:
         return json.dumps(asdict(self), ensure_ascii=False)
@@ -116,6 +125,7 @@ class GoalState:
             last_verdict=data.get("last_verdict"),
             last_reason=data.get("last_reason"),
             paused_reason=data.get("paused_reason"),
+            consecutive_parse_failures=int(data.get("consecutive_parse_failures", 0) or 0),
         )
 
 
@@ -220,13 +230,17 @@ def _truncate(text: str, limit: int) -> str:
 _JSON_OBJECT_RE = re.compile(r"\{.*?\}", re.DOTALL)
 
 
-def _parse_judge_response(raw: str) -> Tuple[bool, str]:
-    """Parse the judge's reply. Fail-open to ``(False, "<reason>")``.
+def _parse_judge_response(raw: str) -> Tuple[bool, str, bool]:
+    """Parse the judge's reply. Fail-open to ``(False, "<reason>", parse_failed)``.
 
-    Returns ``(done, reason)``.
+    Returns ``(done, reason, parse_failed)``. ``parse_failed`` is True when the
+    judge returned output that couldn't be interpreted as the expected JSON
+    verdict (empty body, prose, malformed JSON). Callers use that flag to
+    auto-pause after N consecutive parse failures so a weak judge model
+    doesn't silently burn the turn budget.
     """
     if not raw:
-        return False, "judge returned empty response"
+        return False, "judge returned empty response", True
 
     text = raw.strip()
 
@@ -252,7 +266,7 @@ def _parse_judge_response(raw: str) -> Tuple[bool, str]:
                 data = None
 
     if not isinstance(data, dict):
-        return False, f"judge reply was not JSON: {_truncate(raw, 200)!r}"
+        return False, f"judge reply was not JSON: {_truncate(raw, 200)!r}", True
 
     done_val = data.get("done")
     if isinstance(done_val, str):
@@ -262,7 +276,7 @@ def _parse_judge_response(raw: str) -> Tuple[bool, str]:
     reason = str(data.get("reason") or "").strip()
     if not reason:
         reason = "no reason provided"
-    return done, reason
+    return done, reason, False
 
 
 def judge_goal(
@@ -270,36 +284,42 @@ def judge_goal(
     last_response: str,
     *,
     timeout: float = DEFAULT_JUDGE_TIMEOUT,
-) -> Tuple[str, str]:
+) -> Tuple[str, str, bool]:
     """Ask the auxiliary model whether the goal is satisfied.
 
-    Returns ``(verdict, reason)`` where verdict is ``"done"``, ``"continue"``,
-    or ``"skipped"`` (when the judge couldn't be reached).
+    Returns ``(verdict, reason, parse_failed)`` where verdict is ``"done"``,
+    ``"continue"``, or ``"skipped"`` (when the judge couldn't be reached).
 
-    This is deliberately fail-open: any error returns ``("continue", "...")``
-    so a broken judge doesn't wedge progress — the turn budget is the
-    backstop.
+    ``parse_failed`` is True only when the judge call succeeded but its output
+    was unusable (empty or non-JSON). API/transport errors return False — they
+    are transient and should fail-open silently. Callers use this flag to
+    auto-pause after N consecutive parse failures (see
+    ``DEFAULT_MAX_CONSECUTIVE_PARSE_FAILURES``).
+
+    This is deliberately fail-open: any error returns ``("continue", "...", False)``
+    so a broken judge doesn't wedge progress — the turn budget and the
+    consecutive-parse-failures auto-pause are the backstops.
     """
     if not goal.strip():
-        return "skipped", "empty goal"
+        return "skipped", "empty goal", False
     if not last_response.strip():
         # No substantive reply this turn — almost certainly not done yet.
-        return "continue", "empty response (nothing to evaluate)"
+        return "continue", "empty response (nothing to evaluate)", False
 
     try:
         from agent.auxiliary_client import get_text_auxiliary_client
     except Exception as exc:
         logger.debug("goal judge: auxiliary client import failed: %s", exc)
-        return "continue", "auxiliary client unavailable"
+        return "continue", "auxiliary client unavailable", False
 
     try:
         client, model = get_text_auxiliary_client("goal_judge")
     except Exception as exc:
         logger.debug("goal judge: get_text_auxiliary_client failed: %s", exc)
-        return "continue", "auxiliary client unavailable"
+        return "continue", "auxiliary client unavailable", False
 
     if client is None or not model:
-        return "continue", "no auxiliary client configured"
+        return "continue", "no auxiliary client configured", False
 
     prompt = JUDGE_USER_PROMPT_TEMPLATE.format(
         goal=_truncate(goal, 2000),
@@ -319,17 +339,17 @@ def judge_goal(
         )
     except Exception as exc:
         logger.info("goal judge: API call failed (%s) — falling through to continue", exc)
-        return "continue", f"judge error: {type(exc).__name__}"
+        return "continue", f"judge error: {type(exc).__name__}", False
 
     try:
         raw = resp.choices[0].message.content or ""
     except Exception:
         raw = ""
 
-    done, reason = _parse_judge_response(raw)
+    done, reason, parse_failed = _parse_judge_response(raw)
     verdict = "done" if done else "continue"
     logger.info("goal judge: verdict=%s reason=%s", verdict, _truncate(reason, 120))
-    return verdict, reason
+    return verdict, reason, parse_failed
 
 
 # ──────────────────────────────────────────────────────────────────────
@@ -473,10 +493,18 @@ class GoalManager:
         state.turns_used += 1
         state.last_turn_at = time.time()
 
-        verdict, reason = judge_goal(state.goal, last_response)
+        verdict, reason, parse_failed = judge_goal(state.goal, last_response)
         state.last_verdict = verdict
         state.last_reason = reason
 
+        # Track consecutive judge parse failures. Reset on any usable reply,
+        # including API / transport errors (parse_failed=False) so a flaky
+        # network doesn't trip the auto-pause meant for bad judge models.
+        if parse_failed:
+            state.consecutive_parse_failures += 1
+        else:
+            state.consecutive_parse_failures = 0
+
         if verdict == "done":
             state.status = "done"
             save_goal(self.session_id, state)
@@ -489,6 +517,36 @@ class GoalManager:
                 "message": f"✓ Goal achieved: {reason}",
             }
 
+        # Auto-pause when the judge model can't produce the expected JSON
+        # verdict N turns in a row. Points the user at the goal_judge config
+        # so they can route this side task to a model that follows the
+        # contract (e.g. google/gemini-3-flash-preview). Without this guard,
+        # weak judge models burn the entire turn budget returning prose or
+        # empty strings.
+        if state.consecutive_parse_failures >= DEFAULT_MAX_CONSECUTIVE_PARSE_FAILURES:
+            state.status = "paused"
+            state.paused_reason = (
+                f"judge model returned unparseable output {state.consecutive_parse_failures} turns in a row"
+            )
+            save_goal(self.session_id, state)
+            return {
+                "status": "paused",
+                "should_continue": False,
+                "continuation_prompt": None,
+                "verdict": "continue",
+                "reason": reason,
+                "message": (
+                    f"⏸ Goal paused — the judge model ({state.consecutive_parse_failures} turns) "
+                    "isn't returning the required JSON verdict. Route the judge to a stricter "
+                    "model in ~/.hermes/config.yaml:\n"
+                    "  auxiliary:\n"
+                    "    goal_judge:\n"
+                    "      provider: openrouter\n"
+                    "      model: google/gemini-3-flash-preview\n"
+                    "Then /goal resume to continue."
+                ),
+            }
+
         if state.turns_used >= state.max_turns:
             state.status = "paused"
             state.paused_reason = f"turn budget exhausted ({state.turns_used}/{state.max_turns})"

hermes_cli/kanban.py

@@ -70,6 +70,7 @@ def _task_to_dict(t: kb.Task) -> dict[str, Any]:
         "completed_at": t.completed_at,
         "result": t.result,
         "skills": list(t.skills) if t.skills else [],
+        "max_retries": t.max_retries,
     }
 
 
@@ -284,6 +285,15 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
                                "(repeatable). Appended to the built-in "
                                "kanban-worker skill. Example: "
                                "--skill translation --skill github-code-review")
+    p_create.add_argument("--max-retries", type=int, default=None,
+                          metavar="N",
+                          help="Per-task override for the consecutive-failure "
+                               "circuit breaker. Trip on the Nth failure — "
+                               "e.g. --max-retries 1 blocks on the first "
+                               "failure (no retries), --max-retries 3 allows "
+                               "two retries. Omit to use the dispatcher's "
+                               "kanban.failure_limit config "
+                               f"(default {kb.DEFAULT_FAILURE_LIMIT}).")
     p_create.add_argument("--json", action="store_true", help="Emit JSON output")
 
     # --- list ---
@@ -443,8 +453,8 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
                         help="Cap number of spawns this pass")
     p_disp.add_argument("--failure-limit", type=int,
                         default=kb.DEFAULT_SPAWN_FAILURE_LIMIT,
-                        help=f"Auto-block a task after this many consecutive spawn failures "
-                             f"(default: {kb.DEFAULT_SPAWN_FAILURE_LIMIT})")
+                        help=f"Auto-block a task after this many consecutive non-success attempts "
+                             f"(spawn_failed, timed_out, or crashed; default: {kb.DEFAULT_SPAWN_FAILURE_LIMIT})")
     p_disp.add_argument("--json", action="store_true")
 
     # --- daemon (deprecated) ---
@@ -560,6 +570,42 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
     )
     p_ctx.add_argument("task_id")
 
+    # --- specify --- (triage → todo via auxiliary LLM)
+    p_specify = sub.add_parser(
+        "specify",
+        help="Flesh out a triage-column task into a concrete spec "
+             "(title + body) and promote it to todo. Uses the auxiliary "
+             "LLM configured under auxiliary.triage_specifier.",
+    )
+    p_specify.add_argument(
+        "task_id",
+        nargs="?",
+        default=None,
+        help="Task id to specify (required unless --all is given)",
+    )
+    p_specify.add_argument(
+        "--all",
+        dest="all_triage",
+        action="store_true",
+        help="Specify every task currently in the triage column",
+    )
+    p_specify.add_argument(
+        "--tenant",
+        default=None,
+        help="When used with --all, restrict the sweep to this tenant",
+    )
+    p_specify.add_argument(
+        "--author",
+        default=None,
+        help="Author name recorded on the audit comment "
+             "(default: $HERMES_PROFILE or 'specifier')",
+    )
+    p_specify.add_argument(
+        "--json",
+        action="store_true",
+        help="Emit one JSON object per task on stdout",
+    )
+
     # --- gc ---
     p_gc = sub.add_parser(
         "gc", help="Garbage-collect archived-task workspaces, old events, and old logs",
@@ -674,6 +720,7 @@ def kanban_command(args: argparse.Namespace) -> int:
         "notify-list":        _cmd_notify_list,
         "notify-unsubscribe": _cmd_notify_unsubscribe,
         "context":  _cmd_context,
+        "specify":  _cmd_specify,
         "gc":       _cmd_gc,
     }
     handler = handlers.get(action)
@@ -982,6 +1029,14 @@ def _cmd_create(args: argparse.Namespace) -> int:
     except ValueError as exc:
         print(f"kanban: --max-runtime: {exc}", file=sys.stderr)
         return 2
+    max_retries = getattr(args, "max_retries", None)
+    if max_retries is not None and max_retries < 1:
+        print(
+            f"kanban: --max-retries must be >= 1 (got {max_retries}); "
+            "use 1 to trip on the first failure.",
+            file=sys.stderr,
+        )
+        return 2
     with kb.connect() as conn:
         task_id = kb.create_task(
             conn,
@@ -998,6 +1053,7 @@ def _cmd_create(args: argparse.Namespace) -> int:
             idempotency_key=getattr(args, "idempotency_key", None),
             max_runtime_seconds=max_runtime,
             skills=getattr(args, "skills", None) or None,
+            max_retries=max_retries,
         )
         task = kb.get_task(conn, task_id)
     if getattr(args, "json", False):
@@ -1125,6 +1181,23 @@ def _cmd_show(args: argparse.Namespace) -> int:
           (f" @ {task.workspace_path}" if task.workspace_path else ""))
     if task.skills:
         print(f"  skills:    {', '.join(task.skills)}")
+    # Effective retry threshold. Show the per-task override if set,
+    # otherwise the dispatcher's resolved value from config (or the
+    # default if config doesn't set it either). Helps operators see
+    # why a task auto-blocked earlier/later than they expected.
+    if task.max_retries is not None:
+        print(f"  max-retries: {task.max_retries} (task)")
+    else:
+        try:
+            from hermes_cli.config import load_config
+            cfg = load_config()
+            cfg_val = (cfg.get("kanban", {}) or {}).get("failure_limit")
+        except Exception:
+            cfg_val = None
+        if cfg_val is not None and int(cfg_val) != kb.DEFAULT_FAILURE_LIMIT:
+            print(f"  max-retries: {int(cfg_val)} (config kanban.failure_limit)")
+        else:
+            print(f"  max-retries: {kb.DEFAULT_FAILURE_LIMIT} (default)")
     print(f"  created:   {_fmt_ts(task.created_at)} by {task.created_by or '-'}")
 
     # Diagnostics section — surface active distress signals at the top
@@ -1657,6 +1730,7 @@ def _cmd_daemon(args: argparse.Namespace) -> int:
             "    kanban:\n"
             "      dispatch_in_gateway: true      # default\n"
             "      dispatch_interval_seconds: 60\n"
+            "      failure_limit: 2              # consecutive non-success attempts before auto-block\n"
             "\n"
             "Running both the gateway AND this standalone daemon will\n"
             "race for claims. If you truly need the old standalone\n"
@@ -1943,6 +2017,80 @@ def _cmd_context(args: argparse.Namespace) -> int:
     return 0
 
 
+def _cmd_specify(args: argparse.Namespace) -> int:
+    """Flesh out a triage task (or all of them) via auxiliary LLM,
+    then promote to todo. Thin wrapper over ``kanban_specify``."""
+    from hermes_cli import kanban_specify as spec
+
+    all_flag = bool(getattr(args, "all_triage", False))
+    tenant = getattr(args, "tenant", None)
+    author = getattr(args, "author", None) or _profile_author()
+    want_json = bool(getattr(args, "json", False))
+
+    if args.task_id and all_flag:
+        print(
+            "kanban: pass either a task id OR --all, not both",
+            file=sys.stderr,
+        )
+        return 2
+
+    if all_flag:
+        ids = spec.list_triage_ids(tenant=tenant)
+        if not ids:
+            msg = (
+                "No triage tasks"
+                + (f" for tenant {tenant!r}" if tenant else "")
+                + "."
+            )
+            if want_json:
+                print(json.dumps({"specified": 0, "total": 0}))
+            else:
+                print(msg)
+            return 0
+    elif args.task_id:
+        ids = [args.task_id]
+    else:
+        print(
+            "kanban: specify requires a task id or --all",
+            file=sys.stderr,
+        )
+        return 2
+
+    ok_count = 0
+    fail_count = 0
+    for tid in ids:
+        outcome = spec.specify_task(tid, author=author)
+        if outcome.ok:
+            ok_count += 1
+        else:
+            fail_count += 1
+        if want_json:
+            print(json.dumps({
+                "task_id": outcome.task_id,
+                "ok": outcome.ok,
+                "reason": outcome.reason,
+                "new_title": outcome.new_title,
+            }))
+        else:
+            if outcome.ok:
+                title_suffix = (
+                    f" — retitled: {outcome.new_title!r}"
+                    if outcome.new_title
+                    else ""
+                )
+                print(f"Specified {outcome.task_id} → todo{title_suffix}")
+            else:
+                print(
+                    f"kanban: specify {outcome.task_id}: {outcome.reason}",
+                    file=sys.stderr,
+                )
+    if not all_flag:
+        return 0 if ok_count == 1 else 1
+    # --all: succeed if at least one promotion landed; exit 1 only when
+    # every candidate failed (honest signal for scripts).
+    return 0 if (ok_count > 0 or not ids) else 1
+
+
 def _cmd_gc(args: argparse.Namespace) -> int:
     """Remove scratch workspaces of archived tasks, prune old events, and
     delete old worker logs."""

hermes_cli/kanban_db.py

@@ -595,6 +595,14 @@ class Task:
     # JSON array of skill names. None = use only the defaults; empty
     # list = explicitly no extra skills.
     skills: Optional[list] = None
+    # Per-task override for the consecutive-failure circuit breaker.
+    # The value is the failure count at which the breaker trips — e.g.
+    # ``max_retries=1`` blocks on the first failure (zero retries),
+    # ``max_retries=3`` blocks on the third (two retries allowed).
+    # ``None`` (the common case) falls through to the dispatcher-level
+    # ``kanban.failure_limit`` config, and then to ``DEFAULT_FAILURE_LIMIT``.
+    # Name matches the ``--max-retries`` CLI flag on ``kanban create``.
+    max_retries: Optional[int] = None
 
     @classmethod
     def from_row(cls, row: sqlite3.Row) -> "Task":
@@ -656,6 +664,9 @@ class Task:
                 row["current_step_key"] if "current_step_key" in keys else None
             ),
             skills=skills_value,
+            max_retries=(
+                row["max_retries"] if "max_retries" in keys else None
+            ),
         )
 
 
@@ -776,7 +787,13 @@ CREATE TABLE IF NOT EXISTS tasks (
     -- Force-loaded skills for the worker on this task, stored as JSON.
     -- Appended to the dispatcher's built-in `--skills kanban-worker`.
     -- NULL or empty array = no extras.
-    skills               TEXT
+    skills               TEXT,
+    -- Per-task override for the consecutive-failure circuit breaker.
+    -- The value is the failure count at which the breaker trips — e.g.
+    -- ``max_retries=1`` blocks on the first failure. NULL (the common
+    -- case) falls through to the dispatcher-level ``kanban.failure_limit``
+    -- config and then ``DEFAULT_FAILURE_LIMIT``.
+    max_retries          INTEGER
 );
 
 CREATE TABLE IF NOT EXISTS task_links (
@@ -1008,6 +1025,14 @@ def _migrate_add_optional_columns(conn: sqlite3.Connection) -> None:
         # for existing rows.
         conn.execute("ALTER TABLE tasks ADD COLUMN skills TEXT")
 
+    if "max_retries" not in cols:
+        # Per-task override for the consecutive-failure circuit breaker.
+        # NULL = fall through to the dispatcher-level ``kanban.failure_limit``
+        # config, then ``DEFAULT_FAILURE_LIMIT``. Existing rows get NULL,
+        # which is the correct default (they keep the global behaviour
+        # they were getting before the column existed).
+        conn.execute("ALTER TABLE tasks ADD COLUMN max_retries INTEGER")
+
     # task_events gained a run_id column; back-fill it as NULL for
     # historical events (they predate runs and can't be attributed).
     ev_cols = {row["name"] for row in conn.execute("PRAGMA table_info(task_events)")}
@@ -1163,6 +1188,7 @@ def create_task(
     idempotency_key: Optional[str] = None,
     max_runtime_seconds: Optional[int] = None,
     skills: Optional[Iterable[str]] = None,
+    max_retries: Optional[int] = None,
 ) -> str:
     """Create a new task and optionally link it under parent tasks.
 
@@ -1276,8 +1302,9 @@ def create_task(
                     INSERT INTO tasks (
                         id, title, body, assignee, status, priority,
                         created_by, created_at, workspace_kind, workspace_path,
-                        tenant, idempotency_key, max_runtime_seconds, skills
-                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                        tenant, idempotency_key, max_runtime_seconds, skills,
+                        max_retries
+                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
                     """,
                     (
                         task_id,
@@ -1294,6 +1321,7 @@ def create_task(
                         idempotency_key,
                         int(max_runtime_seconds) if max_runtime_seconds else None,
                         json.dumps(skills_list) if skills_list is not None else None,
+                        int(max_retries) if max_retries is not None else None,
                     ),
                 )
                 for pid in parents:
@@ -1380,7 +1408,7 @@ def assign_task(conn: sqlite3.Connection, task_id: str, profile: Optional[str])
     profile = _canonical_assignee(profile)
     with write_txn(conn):
         row = conn.execute(
-            "SELECT status, claim_lock FROM tasks WHERE id = ?", (task_id,)
+            "SELECT status, claim_lock, assignee FROM tasks WHERE id = ?", (task_id,)
         ).fetchone()
         if not row:
             return False
@@ -1389,7 +1417,17 @@ def assign_task(conn: sqlite3.Connection, task_id: str, profile: Optional[str])
                 f"cannot reassign {task_id}: currently running (claimed). "
                 "Wait for completion or reclaim the stale lock first."
             )
-        conn.execute("UPDATE tasks SET assignee = ? WHERE id = ?", (profile, task_id))
+        if row["assignee"] != profile:
+            # The retry guard is scoped to the task/profile combination. A
+            # human reassigning the task is an explicit recovery action, so the
+            # new profile should not inherit the previous profile's streak.
+            conn.execute(
+                "UPDATE tasks SET assignee = ?, consecutive_failures = 0, "
+                "last_failure_error = NULL WHERE id = ?",
+                (profile, task_id),
+            )
+        else:
+            conn.execute("UPDATE tasks SET assignee = ? WHERE id = ?", (profile, task_id))
         _append_event(conn, task_id, "assigned", {"assignee": profile})
         return True
 
@@ -1859,34 +1897,47 @@ def heartbeat_claim(
         return False
 
 
-def release_stale_claims(conn: sqlite3.Connection) -> int:
+def release_stale_claims(
+    conn: sqlite3.Connection,
+    *,
+    signal_fn=None,
+) -> int:
     """Reset any ``running`` task whose claim has expired.
 
     Returns the number of stale claims reclaimed.  Safe to call often.
     """
     now = int(time.time())
     reclaimed = 0
-    with write_txn(conn):
-        stale = conn.execute(
-            "SELECT id, claim_lock FROM tasks "
-            "WHERE status = 'running' AND claim_expires IS NOT NULL AND claim_expires < ?",
-            (now,),
-        ).fetchall()
-        for row in stale:
-            conn.execute(
+    stale = conn.execute(
+        "SELECT id, claim_lock, worker_pid FROM tasks "
+        "WHERE status = 'running' AND claim_expires IS NOT NULL AND claim_expires < ?",
+        (now,),
+    ).fetchall()
+    for row in stale:
+        termination = _terminate_reclaimed_worker(
+            row["worker_pid"], row["claim_lock"], signal_fn=signal_fn,
+        )
+        with write_txn(conn):
+            cur = conn.execute(
                 "UPDATE tasks SET status = 'ready', claim_lock = NULL, "
                 "claim_expires = NULL, worker_pid = NULL "
-                "WHERE id = ? AND status = 'running'",
-                (row["id"],),
+                "WHERE id = ? AND status = 'running' AND claim_lock IS ? "
+                "AND claim_expires IS NOT NULL AND claim_expires < ?",
+                (row["id"], row["claim_lock"], now),
             )
+            if cur.rowcount != 1:
+                continue
             run_id = _end_run(
                 conn, row["id"],
                 outcome="reclaimed", status="reclaimed",
                 error=f"stale_lock={row['claim_lock']}",
+                metadata=termination,
             )
+            payload = {"stale_lock": row["claim_lock"]}
+            payload.update(termination)
             _append_event(
                 conn, row["id"], "reclaimed",
-                {"stale_lock": row["claim_lock"]},
+                payload,
                 run_id=run_id,
             )
             reclaimed += 1
@@ -1898,6 +1949,7 @@ def reclaim_task(
     task_id: str,
     *,
     reason: Optional[str] = None,
+    signal_fn=None,
 ) -> bool:
     """Operator-driven reclaim: release the claim and reset to ``ready``.
 
@@ -1910,24 +1962,29 @@ def reclaim_task(
     Returns True if a reclaim happened, False if the task isn't in a
     reclaimable state (not running, or doesn't exist).
     """
+    row = conn.execute(
+        "SELECT status, claim_lock, worker_pid FROM tasks WHERE id = ?",
+        (task_id,),
+    ).fetchone()
+    if not row:
+        return False
+    if row["status"] != "running" and row["claim_lock"] is None:
+        # Nothing to reclaim — already ready / blocked / done.
+        return False
+    prev_lock = row["claim_lock"]
+    termination = _terminate_reclaimed_worker(
+        row["worker_pid"], prev_lock, signal_fn=signal_fn,
+    )
     with write_txn(conn):
-        row = conn.execute(
-            "SELECT status, claim_lock, worker_pid FROM tasks WHERE id = ?",
-            (task_id,),
-        ).fetchone()
-        if not row:
-            return False
-        if row["status"] != "running" and row["claim_lock"] is None:
-            # Nothing to reclaim — already ready / blocked / done.
-            return False
-        prev_lock = row["claim_lock"]
-        prev_pid = row["worker_pid"]
-        conn.execute(
+        cur = conn.execute(
             "UPDATE tasks SET status = 'ready', claim_lock = NULL, "
             "claim_expires = NULL, worker_pid = NULL "
-            "WHERE id = ? AND status IN ('running', 'ready', 'blocked')",
-            (task_id,),
+            "WHERE id = ? AND status IN ('running', 'ready', 'blocked') "
+            "AND claim_lock IS ?",
+            (task_id, prev_lock),
         )
+        if cur.rowcount != 1:
+            return False
         run_id = _end_run(
             conn, task_id,
             outcome="reclaimed", status="reclaimed",
@@ -1935,15 +1992,17 @@ def reclaim_task(
                 f"manual_reclaim: {reason}" if reason
                 else f"manual_reclaim lock={prev_lock}"
             ),
+            metadata=termination,
         )
+        payload = {
+            "manual": True,
+            "reason": reason,
+            "prev_lock": prev_lock,
+        }
+        payload.update(termination)
         _append_event(
             conn, task_id, "reclaimed",
-            {
-                "manual": True,
-                "reason": reason,
-                "prev_lock": prev_lock,
-                "prev_pid": prev_pid,
-            },
+            payload,
             run_id=run_id,
         )
     # Operator intervention — they've looked at the task, so the
@@ -2444,6 +2503,91 @@ def unblock_task(conn: sqlite3.Connection, task_id: str) -> bool:
         return True
 
 
+def specify_triage_task(
+    conn: sqlite3.Connection,
+    task_id: str,
+    *,
+    title: Optional[str] = None,
+    body: Optional[str] = None,
+    author: Optional[str] = None,
+) -> bool:
+    """Flesh out a triage task and promote it to ``todo``.
+
+    Atomically updates ``title`` / ``body`` (when provided) and transitions
+    ``status: triage -> todo`` in a single write txn. Returns False when
+    the task is missing or not in the ``triage`` column — callers should
+    surface that as "nothing to specify" rather than an error.
+
+    ``todo`` (not ``ready``) is the correct landing column: ``recompute_ready``
+    promotes parent-free / parent-done todos to ``ready`` on the next
+    dispatcher tick, which keeps the normal parent-gating behaviour intact
+    for specified tasks that happen to have open parents.
+
+    ``author`` is recorded on an audit comment only when at least one of
+    ``title`` / ``body`` actually changed — avoids noisy comment spam for
+    status-only promotions.
+    """
+    if title is not None and not title.strip():
+        raise ValueError("title cannot be blank")
+    with write_txn(conn):
+        existing = conn.execute(
+            "SELECT title, body FROM tasks WHERE id = ? AND status = 'triage'",
+            (task_id,),
+        ).fetchone()
+        if existing is None:
+            return False
+        sets: list[str] = ["status = 'todo'"]
+        params: list[Any] = []
+        changed_fields: list[str] = []
+        if title is not None and title.strip() != (existing["title"] or ""):
+            sets.append("title = ?")
+            params.append(title.strip())
+            changed_fields.append("title")
+        if body is not None and (body or "") != (existing["body"] or ""):
+            sets.append("body = ?")
+            params.append(body)
+            changed_fields.append("body")
+        params.append(task_id)
+        cur = conn.execute(
+            f"UPDATE tasks SET {', '.join(sets)} "
+            f"WHERE id = ? AND status = 'triage'",
+            tuple(params),
+        )
+        if cur.rowcount != 1:
+            return False
+        if changed_fields and author and author.strip():
+            # Inline INSERT (rather than ``add_comment``) because we're
+            # already inside this function's write_txn — nested BEGIN
+            # IMMEDIATE would raise OperationalError. We also skip the
+            # 'commented' event that ``add_comment`` emits, since the
+            # 'specified' event below already records the change.
+            conn.execute(
+                "INSERT INTO task_comments (task_id, author, body, created_at) "
+                "VALUES (?, ?, ?, ?)",
+                (
+                    task_id,
+                    author.strip(),
+                    "Specified — updated "
+                    + ", ".join(changed_fields)
+                    + " and promoted to todo.",
+                    int(time.time()),
+                ),
+            )
+        _append_event(
+            conn,
+            task_id,
+            "specified",
+            {"changed_fields": changed_fields} if changed_fields else None,
+        )
+    # Outside the write_txn above, so we don't nest BEGIN IMMEDIATE — the
+    # ready-promotion pass opens its own IMMEDIATE txn. This runs the same
+    # logic the dispatcher would on its next tick, so a specified task
+    # with no open parents flips straight to 'ready' here instead of
+    # idling in 'todo' until the next sweep.
+    recompute_ready(conn)
+    return True
+
+
 def archive_task(conn: sqlite3.Connection, task_id: str) -> bool:
     with write_txn(conn):
         cur = conn.execute(
@@ -2548,11 +2692,11 @@ def set_workspace_path(
 # Dispatcher (one-shot pass)
 # ---------------------------------------------------------------------------
 
-# After this many consecutive `spawn_failed` events on a task, the dispatcher
-# stops retrying and parks the task in ``blocked`` with a reason so a human
-# can investigate. Prevents the dispatcher from thrashing forever on a task
-# whose profile doesn't exist, whose workspace is unmountable, etc.
-DEFAULT_FAILURE_LIMIT = 5
+# After this many consecutive non-success attempts on a task/profile, the
+# dispatcher stops retrying and parks the task in ``blocked`` with a reason so
+# a human can investigate. Prevents retry storms when a worker repeatedly times
+# out, crashes, or cannot spawn.
+DEFAULT_FAILURE_LIMIT = 2
 # Legacy alias — callers / tests still reference the old name.
 DEFAULT_SPAWN_FAILURE_LIMIT = DEFAULT_FAILURE_LIMIT
 
@@ -2587,6 +2731,77 @@ class DispatchResult:
     """Task ids whose workers exceeded ``max_runtime_seconds``."""
 
 
+# Bounded registry of recently-reaped worker child exits, populated by the
+# reap loop at the top of ``dispatch_once`` and consulted by
+# ``detect_crashed_workers`` to classify a dead-pid task.
+#
+# Entry: ``pid -> (raw_wait_status, reaped_at_epoch)``. We keep raw status
+# so both ``os.WIFEXITED`` / ``os.WEXITSTATUS`` and ``os.WIFSIGNALED`` can
+# be consulted. Entries are trimmed by age (and total size cap as a
+# belt-and-braces against unbounded growth on exotic platforms).
+_RECENT_WORKER_EXIT_TTL_SECONDS = 600
+_RECENT_WORKER_EXITS_MAX = 4096
+_recent_worker_exits: "dict[int, tuple[int, float]]" = {}
+
+
+def _record_worker_exit(pid: int, raw_status: int) -> None:
+    """Record a reaped child's exit status for later classification.
+
+    Called from the reap loop in ``dispatch_once``. Safe to call many
+    times; duplicate pids overwrite (pids can cycle, latest wins).
+    """
+    if not pid or pid <= 0:
+        return
+    now = time.time()
+    _recent_worker_exits[int(pid)] = (int(raw_status), now)
+    # Age-based trim: drop entries older than the TTL.
+    if len(_recent_worker_exits) > _RECENT_WORKER_EXITS_MAX // 2:
+        cutoff = now - _RECENT_WORKER_EXIT_TTL_SECONDS
+        for _pid in [p for p, (_s, t) in _recent_worker_exits.items() if t < cutoff]:
+            _recent_worker_exits.pop(_pid, None)
+    # Size cap as a final guard.
+    if len(_recent_worker_exits) > _RECENT_WORKER_EXITS_MAX:
+        # Drop oldest half.
+        ordered = sorted(_recent_worker_exits.items(), key=lambda kv: kv[1][1])
+        for _pid, _ in ordered[: len(ordered) // 2]:
+            _recent_worker_exits.pop(_pid, None)
+
+
+def _classify_worker_exit(pid: int) -> "tuple[str, Optional[int]]":
+    """Classify a recently-reaped worker by pid.
+
+    Returns ``(kind, code)`` where ``kind`` is one of:
+
+    * ``"clean_exit"`` — ``WIFEXITED`` with ``WEXITSTATUS == 0``. When the
+      task is still ``running`` in the DB, this is a protocol violation
+      (worker exited without calling ``kanban_complete`` / ``kanban_block``)
+      and should be auto-blocked immediately — retrying will just loop.
+    * ``"nonzero_exit"`` — ``WIFEXITED`` with non-zero status. Real error.
+    * ``"signaled"`` — ``WIFSIGNALED`` (OOM killer, SIGKILL, etc). Real crash.
+    * ``"unknown"`` — pid was not in the reap registry (either reaped by
+      something else, or died between reap tick and liveness check). Fall
+      back to existing crashed-counter behavior.
+
+    ``code`` is the exit status (for ``clean_exit`` / ``nonzero_exit``) or
+    the signal number (for ``signaled``), or ``None`` for ``unknown``.
+    """
+    entry = _recent_worker_exits.get(int(pid))
+    if entry is None:
+        return ("unknown", None)
+    raw, _ = entry
+    try:
+        if os.WIFEXITED(raw):
+            code = os.WEXITSTATUS(raw)
+            if code == 0:
+                return ("clean_exit", 0)
+            return ("nonzero_exit", code)
+        if os.WIFSIGNALED(raw):
+            return ("signaled", os.WTERMSIG(raw))
+    except Exception:
+        pass
+    return ("unknown", None)
+
+
 def _pid_alive(pid: Optional[int]) -> bool:
     """Return True if ``pid`` is still running on this host.
 
@@ -2652,6 +2867,59 @@ def _pid_alive(pid: Optional[int]) -> bool:
     return True
 
 
+def _terminate_reclaimed_worker(
+    pid: Optional[int],
+    claim_lock: Optional[str],
+    *,
+    signal_fn=None,
+) -> dict[str, Any]:
+    """Best-effort host-local worker termination for reclaim paths."""
+    import signal
+
+    info: dict[str, Any] = {
+        "prev_pid": int(pid) if pid else None,
+        "host_local": False,
+        "termination_attempted": False,
+        "terminated": False,
+        "sigkill": False,
+    }
+    if not pid or pid <= 0 or not claim_lock:
+        return info
+
+    host_prefix = f"{_claimer_id().split(':', 1)[0]}:"
+    if not str(claim_lock).startswith(host_prefix):
+        return info
+    info["host_local"] = True
+
+    kill = signal_fn if signal_fn is not None else (
+        os.kill if hasattr(os, "kill") else None
+    )
+    if kill is None:
+        return info
+
+    info["termination_attempted"] = True
+    try:
+        kill(int(pid), signal.SIGTERM)
+    except (ProcessLookupError, OSError):
+        return info
+
+    for _ in range(10):
+        if not _pid_alive(pid):
+            info["terminated"] = True
+            return info
+        time.sleep(0.5)
+
+    if _pid_alive(pid):
+        try:
+            kill(int(pid), signal.SIGKILL)
+            info["sigkill"] = True
+        except (ProcessLookupError, OSError):
+            return info
+
+    info["terminated"] = not _pid_alive(pid)
+    return info
+
+
 def heartbeat_worker(
     conn: sqlite3.Connection,
     task_id: str,
@@ -2840,12 +3108,22 @@ def detect_crashed_workers(conn: sqlite3.Connection) -> list[str]:
     are meaningless here. The host-local check is enough because
     ``_default_spawn`` always runs the worker on the same host as the
     dispatcher (the whole design is single-host).
+
+    When the reap registry shows the worker exited cleanly (rc=0) but
+    the task was still ``running`` in the DB, treat it as a protocol
+    violation (worker answered conversationally without calling
+    ``kanban_complete`` / ``kanban_block``) and trip the circuit breaker
+    on the first occurrence — retrying a worker whose CLI keeps
+    returning 0 without a terminal transition just loops forever.
     """
     crashed: list[str] = []
     # Per-crash details collected inside the main txn, used after it
     # closes to run ``_record_task_failure`` (which needs its own
-    # write_txn so can't nest).
-    crash_details: list[tuple[str, int, str]] = []  # (task_id, pid, claimer)
+    # write_txn so can't nest). ``protocol_violation`` flags the
+    # clean-exit-but-still-running case so we can trip the breaker
+    # immediately instead of incrementing by 1.
+    crash_details: list[tuple[str, int, str, bool, str]] = []
+    # (task_id, pid, claimer, protocol_violation, error_text)
     with write_txn(conn):
         rows = conn.execute(
             "SELECT id, worker_pid, claim_lock FROM tasks "
@@ -2859,6 +3137,39 @@ def detect_crashed_workers(conn: sqlite3.Connection) -> list[str]:
                 continue
             if _pid_alive(row["worker_pid"]):
                 continue
+
+            pid = int(row["worker_pid"])
+            kind, code = _classify_worker_exit(pid)
+            if kind == "clean_exit":
+                # Worker subprocess returned 0 but its task is still
+                # ``running`` in the DB — it exited without calling
+                # ``kanban_complete`` / ``kanban_block``. Retrying won't
+                # help.
+                protocol_violation = True
+                error_text = (
+                    "worker exited cleanly (rc=0) without calling "
+                    "kanban_complete or kanban_block — protocol violation"
+                )
+                event_kind = "protocol_violation"
+                event_payload = {
+                    "pid": pid,
+                    "claimer": row["claim_lock"],
+                    "exit_code": code,
+                }
+            else:
+                protocol_violation = False
+                if kind == "nonzero_exit":
+                    error_text = f"pid {pid} exited with code {code}"
+                elif kind == "signaled":
+                    error_text = f"pid {pid} killed by signal {code}"
+                else:
+                    error_text = f"pid {pid} not alive"
+                event_kind = "crashed"
+                event_payload = {"pid": pid, "claimer": row["claim_lock"]}
+                if code is not None and kind != "unknown":
+                    event_payload["exit_kind"] = kind
+                    event_payload["exit_code"] = code
+
             cur = conn.execute(
                 "UPDATE tasks SET status = 'ready', claim_lock = NULL, "
                 "claim_expires = NULL, worker_pid = NULL "
@@ -2869,34 +3180,47 @@ def detect_crashed_workers(conn: sqlite3.Connection) -> list[str]:
                 run_id = _end_run(
                     conn, row["id"],
                     outcome="crashed", status="crashed",
-                    error=f"pid {int(row['worker_pid'])} not alive",
-                    metadata={
-                        "pid": int(row["worker_pid"]),
-                        "claimer": row["claim_lock"],
-                    },
+                    error=error_text,
+                    metadata=dict(event_payload),
                 )
                 _append_event(
-                    conn, row["id"], "crashed",
-                    {"pid": int(row["worker_pid"]), "claimer": row["claim_lock"]},
+                    conn, row["id"], event_kind,
+                    event_payload,
                     run_id=run_id,
                 )
                 crashed.append(row["id"])
                 crash_details.append(
-                    (row["id"], int(row["worker_pid"]), row["claim_lock"])
+                    (row["id"], pid, row["claim_lock"],
+                     protocol_violation, error_text)
                 )
     # Outside the main txn: increment the unified failure counter for
     # each crashed task. If the breaker trips, the task transitions
     # ready → blocked with a ``gave_up`` event on top of the ``crashed``
     # event we already emitted.
-    for tid, pid, claimer in crash_details:
-        _record_task_failure(
+    #
+    # Protocol-violation crashes force an immediate trip (failure_limit=1)
+    # because clean-exit-without-transition is deterministic: the next
+    # respawn will do exactly the same thing. Better to surface to a
+    # human with a clear reason than to loop ``DEFAULT_FAILURE_LIMIT``
+    # times first.
+    auto_blocked: list[str] = []
+    for tid, pid, claimer, protocol_violation, error_text in crash_details:
+        tripped = _record_task_failure(
             conn, tid,
-            error=f"pid {pid} not alive",
+            error=error_text,
             outcome="crashed",
+            failure_limit=(1 if protocol_violation else None),
             release_claim=False,
             end_run=False,
             event_payload_extra={"pid": pid, "claimer": claimer},
         )
+        if tripped:
+            auto_blocked.append(tid)
+    # Stash auto-blocked ids on the function for the dispatch loop to pick up.
+    # Keeps the public return type (``list[str]``) stable for direct callers
+    # and tests that destructure the result; ``dispatch_once`` reads this
+    # side-channel attribute to populate ``DispatchResult.auto_blocked``.
+    detect_crashed_workers._last_auto_blocked = auto_blocked  # type: ignore[attr-defined]
     return crashed
 
 
@@ -2938,20 +3262,39 @@ def _record_task_failure(
     ``event_payload_extra`` merges into the ``gave_up`` event payload
     when the breaker trips, so callers can include outcome-specific
     context (e.g. pid on crash, elapsed on timeout).
+
+    Resolution order for the effective threshold:
+      1. per-task ``max_retries`` if set (nothing else overrides)
+      2. caller-supplied ``failure_limit`` (gateway passes the config
+         value from ``kanban.failure_limit``; tests pass fixed values)
+      3. ``DEFAULT_FAILURE_LIMIT``
     """
     if failure_limit is None:
         failure_limit = DEFAULT_FAILURE_LIMIT
     blocked = False
     with write_txn(conn):
         row = conn.execute(
-            "SELECT consecutive_failures, status FROM tasks WHERE id = ?", (task_id,),
+            "SELECT consecutive_failures, status, max_retries "
+            "FROM tasks WHERE id = ?", (task_id,),
         ).fetchone()
         if row is None:
             return False
         failures = int(row["consecutive_failures"]) + 1
         cur_status = row["status"]
 
-        if failures >= failure_limit:
+        # Per-task override wins over both caller-supplied and default
+        # thresholds. None (the common case) falls through.
+        task_override = (
+            row["max_retries"] if "max_retries" in row.keys() else None
+        )
+        if task_override is not None:
+            effective_limit = int(task_override)
+            limit_source = "task"
+        else:
+            effective_limit = int(failure_limit)
+            limit_source = "dispatcher"
+
+        if failures >= effective_limit:
             # Trip the breaker.
             if release_claim:
                 # Spawn path: still running, also clear claim state.
@@ -2979,10 +3322,17 @@ def _record_task_failure(
                     conn, task_id,
                     outcome="gave_up", status="gave_up",
                     error=error[:500],
-                    metadata={"failures": failures, "trigger_outcome": outcome},
+                    metadata={
+                        "failures": failures,
+                        "trigger_outcome": outcome,
+                        "effective_limit": effective_limit,
+                        "limit_source": limit_source,
+                    },
                 )
             payload = {
                 "failures": failures,
+                "effective_limit": effective_limit,
+                "limit_source": limit_source,
                 "error": error[:500],
                 "trigger_outcome": outcome,
             }
@@ -3150,9 +3500,43 @@ def dispatch_once(
     ``board`` pins workspace/log/db resolution for this tick to a specific
     board. When omitted, the current-board resolution chain is used.
     """
+    # Reap zombie children from previously spawned workers.
+    # The gateway-embedded dispatcher is the parent of every worker spawned
+    # via _default_spawn (start_new_session=True only detaches the
+    # controlling tty, not the parent). Without an explicit waitpid, each
+    # completed worker becomes a <defunct> entry that lingers until gateway
+    # exit. WNOHANG keeps this non-blocking; ChildProcessError means no
+    # children to reap. Bounded: at most one tick's worth of completions
+    # can be in <defunct> at once.
+    #
+    # We also record the exit status keyed by pid, so
+    # ``detect_crashed_workers`` can distinguish a worker that exited
+    # cleanly without calling ``kanban_complete`` / ``kanban_block``
+    # (protocol violation — auto-block) from a real crash (OOM killer,
+    # SIGKILL, non-zero exit — existing counter behavior).
+    try:
+        while True:
+            try:
+                _pid, _status = os.waitpid(-1, os.WNOHANG)
+            except ChildProcessError:
+                break
+            if _pid == 0:
+                break
+            _record_worker_exit(_pid, _status)
+    except Exception:
+        pass
+
     result = DispatchResult()
     result.reclaimed = release_stale_claims(conn)
     result.crashed = detect_crashed_workers(conn)
+    # detect_crashed_workers stashes protocol-violation auto-blocks on
+    # itself so the public list-return stays stable. Pull them into the
+    # DispatchResult here so telemetry / tests see the trip.
+    _crash_auto_blocked = getattr(
+        detect_crashed_workers, "_last_auto_blocked", []
+    )
+    if _crash_auto_blocked:
+        result.auto_blocked.extend(_crash_auto_blocked)
     result.timed_out = enforce_max_runtime(conn)
     result.promoted = recompute_ready(conn)
 

hermes_cli/kanban_specify.py

@@ -0,0 +1,265 @@
+"""Kanban triage specifier — flesh out a one-liner into a real spec.
+
+Used by ``hermes kanban specify [task_id | --all]``. Takes a task that
+lives in the Triage column (a rough idea, typically only a title), calls
+the auxiliary LLM to produce:
+
+  * A tightened title (optional — only replaces if the model proposes a
+    materially different one)
+  * A concrete body: goal, proposed approach, acceptance criteria
+
+and then flips the task ``triage -> todo`` via
+``kanban_db.specify_triage_task``. The dispatcher promotes it to
+``ready`` on its next tick (or immediately if there are no open parents).
+
+Design notes
+------------
+
+* This module intentionally mirrors ``hermes_cli/goals.py`` — same aux
+  client pattern, same "empty config => skip, don't crash" tolerance.
+  Keeps the surface area tiny and the failure modes predictable.
+
+* The prompt is a short system + user pair. We ask for JSON with
+  ``{title, body}``; if parsing fails, we fall back to treating the
+  whole response as the body and leave the title untouched. No
+  retry loop — one shot, keep cost bounded.
+
+* Structured output / JSON mode is not requested explicitly so the
+  specifier works on providers that don't implement it. The parse
+  is lenient (tolerates markdown code fences around the JSON).
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import re
+from dataclasses import dataclass
+from typing import Optional
+
+from hermes_cli import kanban_db as kb
+
+logger = logging.getLogger(__name__)
+
+
+_SYSTEM_PROMPT = """You are the Kanban triage specifier for the Hermes Agent board.
+A user dropped a rough idea into the Triage column. Your job is to turn it
+into a concrete, actionable task spec that an autonomous worker can pick up
+and execute without further clarification.
+
+Output a single JSON object with exactly two keys:
+
+  {
+    "title": "<tightened task title, <= 80 chars, imperative voice>",
+    "body":  "<multi-line spec, see structure below>"
+  }
+
+The body MUST include these sections, each prefixed with a bold markdown
+heading, in this order:
+
+  **Goal** — one sentence, user-facing outcome.
+  **Approach** — 2-5 bullets on how a worker should tackle it.
+  **Acceptance criteria** — checklist of concrete, verifiable conditions.
+  **Out of scope** — short list of things NOT to touch (omit if nothing
+      obvious; never invent scope creep).
+
+Rules:
+  - Keep the tightened title close in meaning to the original idea — do
+    NOT invent a different project.
+  - If the original idea is already detailed, preserve its substance and
+    just reformat into the sections above.
+  - Never add invented requirements the user didn't hint at.
+  - No preamble, no closing remarks, no code fences around the JSON.
+  - Output only the JSON object and nothing else.
+"""
+
+
+_USER_TEMPLATE = """Task id: {task_id}
+Current title: {title}
+Current body:
+{body}
+"""
+
+
+@dataclass
+class SpecifyOutcome:
+    """Result of specifying a single triage task."""
+
+    task_id: str
+    ok: bool
+    reason: str = ""
+    new_title: Optional[str] = None
+
+
+def _truncate(text: str, limit: int) -> str:
+    if len(text) <= limit:
+        return text
+    return text[: limit - 1] + "…"
+
+
+_FENCE_RE = re.compile(r"^\s*```(?:json)?\s*|\s*```\s*$", re.IGNORECASE)
+
+
+def _extract_json_blob(raw: str) -> Optional[dict]:
+    """Lenient JSON extraction — tolerates fenced code blocks and
+    leading/trailing whitespace. Returns None if nothing parses."""
+    if not raw:
+        return None
+    stripped = _FENCE_RE.sub("", raw.strip())
+    # Greedy: find the first `{` and last `}` and try that slice.
+    first = stripped.find("{")
+    last = stripped.rfind("}")
+    if first == -1 or last == -1 or last <= first:
+        return None
+    candidate = stripped[first : last + 1]
+    try:
+        val = json.loads(candidate)
+    except (ValueError, json.JSONDecodeError):
+        return None
+    if not isinstance(val, dict):
+        return None
+    return val
+
+
+def _profile_author() -> str:
+    """Mirror of ``hermes_cli.kanban._profile_author``. Kept local to
+    avoid a circular import when kanban.py imports this module."""
+    return (
+        os.environ.get("HERMES_PROFILE")
+        or os.environ.get("USER")
+        or "specifier"
+    )
+
+
+def specify_task(
+    task_id: str,
+    *,
+    author: Optional[str] = None,
+    timeout: Optional[int] = None,
+) -> SpecifyOutcome:
+    """Specify a single triage task and promote it to ``todo``.
+
+    Returns an outcome describing what happened. Never raises for expected
+    failure modes (task not in triage, no aux client configured, API
+    error, malformed response) — those surface via ``ok=False`` so the
+    ``--all`` sweep can continue past individual failures.
+    """
+    with kb.connect() as conn:
+        task = kb.get_task(conn, task_id)
+    if task is None:
+        return SpecifyOutcome(task_id, False, "unknown task id")
+    if task.status != "triage":
+        return SpecifyOutcome(
+            task_id, False, f"task is not in triage (status={task.status!r})"
+        )
+
+    try:
+        from agent.auxiliary_client import get_text_auxiliary_client
+    except Exception as exc:  # pragma: no cover — import smoke test
+        logger.debug("specify: auxiliary client import failed: %s", exc)
+        return SpecifyOutcome(task_id, False, "auxiliary client unavailable")
+
+    try:
+        client, model = get_text_auxiliary_client("triage_specifier")
+    except Exception as exc:
+        logger.debug("specify: get_text_auxiliary_client failed: %s", exc)
+        return SpecifyOutcome(task_id, False, "auxiliary client unavailable")
+
+    if client is None or not model:
+        return SpecifyOutcome(
+            task_id, False, "no auxiliary client configured"
+        )
+
+    user_msg = _USER_TEMPLATE.format(
+        task_id=task.id,
+        title=_truncate(task.title or "", 400),
+        body=_truncate(task.body or "(no body)", 4000),
+    )
+
+    try:
+        resp = client.chat.completions.create(
+            model=model,
+            messages=[
+                {"role": "system", "content": _SYSTEM_PROMPT},
+                {"role": "user", "content": user_msg},
+            ],
+            temperature=0.3,
+            max_tokens=1500,
+            timeout=timeout or 120,
+        )
+    except Exception as exc:
+        logger.info(
+            "specify: API call failed for %s (%s) — skipping",
+            task_id, exc,
+        )
+        return SpecifyOutcome(
+            task_id, False, f"LLM error: {type(exc).__name__}"
+        )
+
+    try:
+        raw = resp.choices[0].message.content or ""
+    except Exception:
+        raw = ""
+
+    parsed = _extract_json_blob(raw)
+
+    new_title: Optional[str]
+    new_body: Optional[str]
+    if parsed is None:
+        # Fall back: treat the whole reply as the body, leave title as-is.
+        # Worst case the user edits afterward — still better than stranding
+        # the task in triage on a malformed LLM reply.
+        stripped_raw = raw.strip()
+        if not stripped_raw:
+            return SpecifyOutcome(
+                task_id, False, "LLM returned an empty response"
+            )
+        new_title = None
+        new_body = stripped_raw
+    else:
+        title_val = parsed.get("title")
+        body_val = parsed.get("body")
+        new_title = (
+            title_val.strip()
+            if isinstance(title_val, str) and title_val.strip()
+            else None
+        )
+        new_body = (
+            body_val if isinstance(body_val, str) and body_val.strip() else None
+        )
+        if new_body is None and new_title is None:
+            return SpecifyOutcome(
+                task_id, False, "LLM response missing title and body"
+            )
+
+    with kb.connect() as conn:
+        ok = kb.specify_triage_task(
+            conn,
+            task_id,
+            title=new_title,
+            body=new_body,
+            author=author or _profile_author(),
+        )
+    if not ok:
+        # Race: someone else promoted / archived the task between our
+        # read above and the write. Report, don't crash.
+        return SpecifyOutcome(
+            task_id, False, "task moved out of triage before promotion"
+        )
+    return SpecifyOutcome(task_id, True, "specified", new_title=new_title)
+
+
+def list_triage_ids(*, tenant: Optional[str] = None) -> list[str]:
+    """Return task ids currently in the triage column.
+
+    ``tenant`` narrows the sweep; ``None`` returns every triage task.
+    """
+    with kb.connect() as conn:
+        tasks = kb.list_tasks(
+            conn,
+            status="triage",
+            tenant=tenant,
+            include_archived=False,
+        )
+    return [t.id for t in tasks]

hermes_cli/main.py

@@ -230,6 +230,7 @@ except Exception:
     pass  # best-effort — don't crash if config isn't available yet
 
 import logging
+import threading
 import time as _time
 from datetime import datetime
 
@@ -6447,6 +6448,45 @@ def _load_installable_optional_extras() -> list[str]:
     return referenced
 
 
+def _run_install_with_heartbeat(
+    cmd: list[str],
+    *,
+    env: dict[str, str] | None = None,
+    heartbeat_interval_seconds: int = 30,
+) -> None:
+    """Run dependency install command with periodic heartbeat output.
+
+    Some resolvers/build backends (especially when compiling Rust/C extensions)
+    can stay quiet for minutes. Emit a simple elapsed-time heartbeat so users
+    know ``hermes update`` is still progressing even if pip/uv itself is silent.
+    """
+    done = threading.Event()
+    start = _time.time()
+
+    def _heartbeat() -> None:
+        # Wait first, then print, so short installs don't emit noise.
+        while not done.wait(heartbeat_interval_seconds):
+            elapsed = int(_time.time() - start)
+            print(
+                f"  … still installing dependencies ({elapsed}s elapsed)"
+                " — compiling Rust/C extensions can take several minutes",
+                flush=True,
+            )
+
+    t = threading.Thread(target=_heartbeat, daemon=True)
+    t.start()
+    try:
+        subprocess.run(
+            cmd,
+            cwd=PROJECT_ROOT,
+            check=True,
+            env=env,
+        )
+    finally:
+        done.set()
+        t.join(timeout=0.2)
+
+
 def _install_python_dependencies_with_optional_fallback(
     install_cmd_prefix: list[str],
     *,
@@ -6463,12 +6503,13 @@ def _install_python_dependencies_with_optional_fallback(
     Collecting/Building/Installing step), so keeping it visible costs
     nothing on fast hardware and prevents the "hermes update hangs" reports
     on slow hardware.
+
+    We also add periodic heartbeat lines in case the resolver/build backend is
+    itself silent for long stretches.
     """
     try:
-        subprocess.run(
+        _run_install_with_heartbeat(
             install_cmd_prefix + ["install", "-e", ".[all]"],
-            cwd=PROJECT_ROOT,
-            check=True,
             env=env,
         )
         return
@@ -6477,10 +6518,8 @@ def _install_python_dependencies_with_optional_fallback(
             "  ⚠ Optional extras failed, reinstalling base dependencies and retrying extras individually..."
         )
 
-    subprocess.run(
+    _run_install_with_heartbeat(
         install_cmd_prefix + ["install", "-e", "."],
-        cwd=PROJECT_ROOT,
-        check=True,
         env=env,
     )
 
@@ -6488,10 +6527,8 @@ def _install_python_dependencies_with_optional_fallback(
     installed_extras: list[str] = []
     for extra in _load_installable_optional_extras():
         try:
-            subprocess.run(
+            _run_install_with_heartbeat(
                 install_cmd_prefix + ["install", "-e", f".[{extra}]"],
-                cwd=PROJECT_ROOT,
-                check=True,
                 env=env,
             )
             installed_extras.append(extra)
@@ -7337,7 +7374,9 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 for p in all_profiles:
                     try:
                         r = seed_profile_skills(p.path, quiet=True)
-                        if r:
+                        if r and r.get("skipped_opt_out"):
+                            status = "opted out (--no-skills)"
+                        elif r:
                             copied = len(r.get("copied", []))
                             updated = len(r.get("updated", []))
                             modified = len(r.get("user_modified", []))
@@ -7408,11 +7447,8 @@ def _cmd_update_impl(args, gateway_mode: bool):
                     .lower()
                 )
             elif not (sys.stdin.isatty() and sys.stdout.isatty()):
-                print("  ℹ Non-interactive session — skipping config migration prompt.")
-                print(
-                    "    Run 'hermes config migrate' later to apply any new config/env options."
-                )
-                response = "n"
+                print("  ℹ Non-interactive session — applying safe config migrations.")
+                response = "auto"
             else:
                 try:
                     response = (
@@ -7423,19 +7459,22 @@ def _cmd_update_impl(args, gateway_mode: bool):
                 except EOFError:
                     response = "n"
 
-            if response in ("", "y", "yes"):
+            if response in ("", "y", "yes", "auto"):
                 print()
-                # In gateway mode OR under --yes, run auto-migrations only (no
-                # input() prompts for API keys which would hang the detached
-                # process / defeat the point of --yes).
-                results = migrate_config(
-                    interactive=not (gateway_mode or assume_yes), quiet=False
+                # Gateway mode, --yes, and non-interactive update contexts
+                # (dashboard / web server actions) cannot prompt for API keys.
+                # Still run the non-interactive migration pass before restarting
+                # so new default config fields and version bumps are written
+                # before the freshly updated gateway validates config at startup.
+                interactive_migration = not (
+                    gateway_mode or assume_yes or response == "auto"
                 )
+                results = migrate_config(interactive=interactive_migration, quiet=False)
 
                 if results["env_added"] or results["config_added"]:
                     print()
                     print("✓ Configuration updated!")
-                if (gateway_mode or assume_yes) and missing_env:
+                if (gateway_mode or assume_yes or response == "auto") and missing_env:
                     print("  ℹ API keys require manual entry: hermes config migrate")
             else:
                 print()
@@ -7739,6 +7778,23 @@ def _cmd_update_impl(args, gateway_mode: bool):
                             # when the graceful path failed (unit missing
                             # SIGUSR1 wiring, drain exceeded the budget,
                             # restart-policy mismatch).
+                            #
+                            # Always `reset-failed` first.  If systemd's own
+                            # auto-restart attempts already parked the unit
+                            # in a failed state (transient CHDIR / OOM /
+                            # filesystem race after our drain + exit-75),
+                            # a plain `systemctl restart` can wedge against
+                            # the RestartSec backoff and leave the unit
+                            # dead.  Clearing the failed state first makes
+                            # the restart idempotent.  Mirrors the recovery
+                            # path in `hermes gateway restart`
+                            # (`systemd_restart()`) as of PR #20949.
+                            subprocess.run(
+                                scope_cmd + ["reset-failed", svc_name],
+                                capture_output=True,
+                                text=True,
+                                timeout=10,
+                            )
                             restart = subprocess.run(
                                 scope_cmd + ["restart", svc_name],
                                 capture_output=True,
@@ -7758,10 +7814,19 @@ def _cmd_update_impl(args, gateway_mode: bool):
                                 else:
                                     # Retry once — transient startup failures
                                     # (stale module cache, import race) often
-                                    # resolve on the second attempt.
+                                    # resolve on the second attempt.  Again
+                                    # clear any failed state first so the
+                                    # retry isn't blocked by the previous
+                                    # crash.
                                     print(
                                         f"  ⚠ {svc_name} died after restart, retrying..."
                                     )
+                                    subprocess.run(
+                                        scope_cmd + ["reset-failed", svc_name],
+                                        capture_output=True,
+                                        text=True,
+                                        timeout=10,
+                                    )
                                     subprocess.run(
                                         scope_cmd + ["restart", svc_name],
                                         capture_output=True,
@@ -7776,10 +7841,13 @@ def _cmd_update_impl(args, gateway_mode: bool):
                                         restarted_services.append(svc_name)
                                         print(f"  ✓ {svc_name} recovered on retry")
                                     else:
+                                        _scope_flag = "--user " if scope == "user" else ""
                                         print(
                                             f"  ✗ {svc_name} failed to stay running after restart.\n"
-                                            f"    Check logs: journalctl --user -u {svc_name} --since '2 min ago'\n"
-                                            f"    Restart manually: systemctl {'--user ' if scope == 'user' else ''}restart {svc_name}"
+                                            f"    Check logs: journalctl {_scope_flag}-u {svc_name} --since '2 min ago'\n"
+                                            f"    Recover manually:\n"
+                                            f"      systemctl {_scope_flag}reset-failed {svc_name}\n"
+                                            f"      systemctl {_scope_flag}restart {svc_name}"
                                         )
                             else:
                                 print(
@@ -8130,6 +8198,7 @@ def cmd_profile(args):
         clone = getattr(args, "clone", False)
         clone_all = getattr(args, "clone_all", False)
         no_alias = getattr(args, "no_alias", False)
+        no_skills = getattr(args, "no_skills", False)
 
         try:
             clone_from = getattr(args, "clone_from", None)
@@ -8140,6 +8209,7 @@ def cmd_profile(args):
                 clone_all=clone_all,
                 clone_config=clone,
                 no_alias=no_alias,
+                no_skills=no_skills,
             )
             print(f"\nProfile '{name}' created at {profile_dir}")
 
@@ -8164,10 +8234,17 @@ def cmd_profile(args):
                 except Exception:
                     pass  # Honcho plugin not installed or not configured
 
-            # Seed bundled skills (skip if --clone-all already copied them)
+            # Seed bundled skills (skip if --clone-all already copied them, or
+            # if --no-skills was passed — in which case seed_profile_skills()
+            # honors the marker file and returns skipped_opt_out=True).
             if not clone_all:
                 result = seed_profile_skills(profile_dir)
-                if result:
+                if result and result.get("skipped_opt_out"):
+                    print(
+                        "No bundled skills seeded (--no-skills). "
+                        "Delete .no-bundled-skills in the profile to opt back in."
+                    )
+                elif result:
                     copied = len(result.get("copied", []))
                     print(f"{copied} bundled skills synced.")
                 else:
@@ -8685,6 +8762,9 @@ def main():
         help="Target the Linux system-level gateway service",
     )
 
+    # gateway list
+    gateway_subparsers.add_parser("list", help="List all profiles and their gateway status")
+
     # gateway setup
     gateway_subparsers.add_parser("setup", help="Configure messaging platforms")
 
@@ -10002,7 +10082,15 @@ Examples:
     )
     mcp_add_p.add_argument("name", help="Server name (used as config key)")
     mcp_add_p.add_argument("--url", help="HTTP/SSE endpoint URL")
-    mcp_add_p.add_argument("--command", help="Stdio command (e.g. npx)")
+    # dest="mcp_command" so this flag does not clobber the top-level
+    # subparser's args.command attribute, which the dispatcher reads to
+    # route to cmd_mcp.  Without an explicit dest, argparse derives
+    # dest="command" from the flag name and sets it to None when the
+    # flag is omitted, causing `hermes mcp add ...` to fall through to
+    # interactive chat.
+    mcp_add_p.add_argument(
+        "--command", dest="mcp_command", help="Stdio command (e.g. npx)"
+    )
     mcp_add_p.add_argument(
         "--args", nargs="*", default=[], help="Arguments for stdio command"
     )
@@ -10529,6 +10617,11 @@ Examples:
     profile_create.add_argument(
         "--no-alias", action="store_true", help="Skip wrapper script creation"
     )
+    profile_create.add_argument(
+        "--no-skills",
+        action="store_true",
+        help="Create an empty profile with no bundled skills (opts out of `hermes update` skill sync)",
+    )
 
     profile_delete = profile_subparsers.add_parser("delete", help="Delete a profile")
     profile_delete.add_argument("profile_name", help="Profile to delete")

hermes_cli/mcp_config.py

@@ -221,7 +221,10 @@ def cmd_mcp_add(args):
     """Add a new MCP server with discovery-first tool selection."""
     name = args.name
     url = getattr(args, "url", None)
-    command = getattr(args, "command", None)
+    # Read from `mcp_command` (set by --command via explicit dest) — see
+    # mcp_add_p.add_argument("--command", dest="mcp_command", ...) in
+    # hermes_cli/main.py for why the dest is renamed.
+    command = getattr(args, "mcp_command", None)
     cmd_args = getattr(args, "args", None) or []
     auth_type = getattr(args, "auth", None)
     preset_name = getattr(args, "preset", None)

hermes_cli/model_switch.py

@@ -1637,7 +1637,8 @@ def list_authenticated_providers(
                         groups[group_key]["models"].append(m)
 
         _section4_emitted_slugs: set = set()
-        for grp in groups.values():
+        for grp_key, grp in groups.items():
+            api_url, api_key = grp_key
             slug = grp["slug"]
             # If the slug is already claimed by a built-in / overlay /
             # user-provider row (sections 1-3), skip this custom group
@@ -1675,6 +1676,18 @@ def list_authenticated_providers(
             _grp_url_norm = _pair_key[1]
             if _grp_url_norm and _grp_url_norm in _builtin_endpoints:
                 continue
+            # Live model discovery from custom provider endpoints (matches
+            # Section 3 behavior for user ``providers:`` entries).
+            if api_url and api_key:
+                try:
+                    from hermes_cli.models import fetch_api_models
+
+                    live_models = fetch_api_models(api_key, api_url)
+                    if live_models:
+                        grp["models"] = live_models
+                        grp["total_models"] = len(live_models)
+                except Exception:
+                    pass
             results.append({
                 "slug": slug,
                 "name": grp["name"],

hermes_cli/models.py

@@ -46,6 +46,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("xiaomi/mimo-v2.5-pro",             ""),
     ("xiaomi/mimo-v2.5",                 ""),
     ("tencent/hy3-preview:free",         "free"),
+    ("tencent/hy3-preview",              ""),
     ("openai/gpt-5.3-codex",            ""),
     ("google/gemini-3-pro-image-preview", ""),
     ("google/gemini-3-flash-preview",   ""),
@@ -416,6 +417,18 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "glm-4.7",
         "MiniMax-M2.5",
     ],
+    # Alibaba Coding Plan — same platform as alibaba (DashScope coding-intl),
+    # separate provider ID with its own base_url_env_var.
+    "alibaba-coding-plan": [
+        "qwen3.6-plus",
+        "qwen3.5-plus",
+        "qwen3-coder-plus",
+        "qwen3-coder-next",
+        "kimi-k2.5",
+        "glm-5",
+        "glm-4.7",
+        "MiniMax-M2.5",
+    ],
     # Curated HF model list — only agentic models that map to OpenRouter defaults.
     "huggingface": [
         "moonshotai/Kimi-K2.5",

hermes_cli/pairing.py

@@ -73,6 +73,24 @@ def _cmd_approve(store, platform: str, code: str):
         display = f"{name} ({uid})" if name else uid
         print(f"\n  Approved! User {display} on {platform} can now use the bot~")
         print("  They'll be recognized automatically on their next message.\n")
+    elif store._is_locked_out(platform):
+        # Disambiguate: approve_code returns None for both invalid codes
+        # and lockout. Tell the operator it's lockout so they don't chase
+        # a "wrong code" rabbit hole (#10195).
+        import time as _time
+        limits = store._load_json(store._rate_limit_path())
+        lockout_until = limits.get(f"_lockout:{platform}", 0)
+        remaining = max(0, int(lockout_until - _time.time()))
+        mins = remaining // 60
+        print(
+            f"\n  Platform '{platform}' is locked out after too many failed "
+            f"approval attempts."
+        )
+        print(f"  Lockout clears in ~{mins} minute(s).")
+        print(
+            "  To reset sooner, delete the '_lockout:{0}' entry from "
+            "~/.hermes/platforms/pairing/_rate_limits.json\n".format(platform)
+        )
     else:
         print(f"\n  Code '{code}' not found or expired for platform '{platform}'.")
         print("  Run 'hermes pairing list' to see pending codes.\n")

hermes_cli/plugins.py

@@ -80,6 +80,10 @@ VALID_HOOKS: Set[str] = {
     "post_tool_call",
     "transform_terminal_output",
     "transform_tool_result",
+    # Transform LLM output before it's returned to the user.
+    # Plugins return a string to replace the response text, or None/empty to leave unchanged.
+    # First non-None string wins. Useful for vocabulary/personality transformation.
+    "transform_llm_output",
     "pre_llm_call",
     "post_llm_call",
     "pre_api_request",

hermes_cli/profiles.py

@@ -71,6 +71,22 @@ _CLONE_ALL_STRIP = [
     "processes.json",
 ]
 
+# Marker file written by `hermes profile create --no-skills`.  When present in
+# a profile's root, callers of seed_profile_skills() (fresh-create, `hermes
+# update`'s all-profile sync, the web dashboard) skip bundled-skill seeding
+# for that profile.  The user can still install skills manually via
+# `hermes skills install` or drop SKILL.md files into the profile's skills/.
+# Delete the marker file to opt back in.
+NO_BUNDLED_SKILLS_MARKER = ".no-bundled-skills"
+
+
+def has_bundled_skills_opt_out(profile_dir: Path) -> bool:
+    """Return True if the profile opted out of bundled-skill seeding."""
+    try:
+        return (profile_dir / NO_BUNDLED_SKILLS_MARKER).exists()
+    except OSError:
+        return False
+
 
 def _clone_all_copytree_ignore(source_dir: Path):
     """Ignore ``profiles/`` at the root of *source_dir* only.
@@ -427,6 +443,7 @@ def create_profile(
     clone_all: bool = False,
     clone_config: bool = False,
     no_alias: bool = False,
+    no_skills: bool = False,
 ) -> Path:
     """Create a new profile directory.
 
@@ -444,12 +461,22 @@ def create_profile(
         skills, and selected profile identity files from the source profile.
     no_alias:
         If True, skip wrapper script creation.
+    no_skills:
+        If True, create an empty profile with no bundled skills, and write
+        a marker file so ``hermes update`` skips re-seeding this profile's
+        skills. Mutually exclusive with ``clone_config``/``clone_all`` (those
+        explicitly copy skills from the source).
 
     Returns
     -------
     Path
         The newly created profile directory.
     """
+    if no_skills and (clone_config or clone_all):
+        raise ValueError(
+            "--no-skills is mutually exclusive with --clone / --clone-all "
+            "(cloning explicitly copies skills from the source profile)."
+        )
     canon = normalize_profile_name(name)
     validate_profile_name(canon)
 
@@ -527,6 +554,19 @@ def create_profile(
         except Exception:
             pass  # best-effort — don't fail profile creation over this
 
+    # Write the opt-out marker so seed_profile_skills() and `hermes update`'s
+    # all-profile sync loop both skip this profile for bundled-skill seeding.
+    if no_skills:
+        try:
+            (profile_dir / NO_BUNDLED_SKILLS_MARKER).write_text(
+                "This profile opted out of bundled-skill seeding "
+                "(`hermes profile create --no-skills`).\n"
+                "Delete this file to re-enable sync on the next `hermes update`.\n",
+                encoding="utf-8",
+            )
+        except OSError:
+            pass  # best-effort — the feature still works via the empty skills/ dir
+
     return profile_dir
 
 
@@ -535,7 +575,19 @@ def seed_profile_skills(profile_dir: Path, quiet: bool = False) -> Optional[dict
 
     Uses subprocess because sync_skills() caches HERMES_HOME at module level.
     Returns the sync result dict, or None on failure.
+
+    Profiles that opted out of bundled skills (via ``hermes profile create
+    --no-skills`` — which writes ``.no-bundled-skills`` to the profile root)
+    are skipped and get an empty-result dict so callers can report
+    "opted out" instead of "failed".
     """
+    if has_bundled_skills_opt_out(profile_dir):
+        return {
+            "copied": [],
+            "updated": [],
+            "user_modified": [],
+            "skipped_opt_out": True,
+        }
     project_root = Path(__file__).parent.parent.resolve()
     try:
         result = subprocess.run(

hermes_cli/runtime_provider.py

@@ -319,9 +319,10 @@ def _try_resolve_from_custom_pool(
     base_url: str,
     provider_label: str,
     api_mode_override: Optional[str] = None,
+    provider_name: Optional[str] = None,
 ) -> Optional[Dict[str, Any]]:
     """Check if a credential pool exists for a custom endpoint and return a runtime dict if so."""
-    pool_key = get_custom_provider_pool_key(base_url)
+    pool_key = get_custom_provider_pool_key(base_url, provider_name=provider_name)
     if not pool_key:
         return None
     try:
@@ -521,7 +522,7 @@ def _resolve_named_custom_runtime(
         return None
 
     # Check if a credential pool exists for this custom endpoint
-    pool_result = _try_resolve_from_custom_pool(base_url, "custom", custom_provider.get("api_mode"))
+    pool_result = _try_resolve_from_custom_pool(base_url, "custom", custom_provider.get("api_mode"), provider_name=custom_provider.get("name"))
     if pool_result:
         # Propagate the model name even when using pooled credentials —
         # the pool doesn't know about the custom_providers model field.
@@ -640,8 +641,11 @@ def _resolve_openrouter_runtime(
 
     # For custom endpoints, check if a credential pool exists
     if effective_provider == "custom" and base_url:
+        # Pass requested_provider so pool lookup prefers name match over base_url,
+        # fixing credential mix-ups when multiple custom providers share a base_url.
         pool_result = _try_resolve_from_custom_pool(
             base_url, effective_provider, _parse_api_mode(model_cfg.get("api_mode")),
+            provider_name=requested_provider if requested_norm != "custom" else None,
         )
         if pool_result:
             return pool_result

hermes_cli/setup.py

@@ -2462,6 +2462,9 @@ def setup_gateway(config: dict):
             launchd_start,
             launchd_restart,
             UserSystemdUnavailableError,
+            SystemScopeRequiresRootError,
+            _system_scope_wizard_would_need_root,
+            _print_system_scope_remediation,
         )
 
         service_installed = _is_service_installed()
@@ -2479,7 +2482,9 @@ def setup_gateway(config: dict):
             print()
 
         if service_running:
-            if prompt_yes_no("  Restart the gateway to pick up changes?", True):
+            if supports_systemd and _system_scope_wizard_would_need_root():
+                _print_system_scope_remediation("restart")
+            elif prompt_yes_no("  Restart the gateway to pick up changes?", True):
                 try:
                     if supports_systemd:
                         systemd_restart()
@@ -2489,10 +2494,19 @@ def setup_gateway(config: dict):
                     print_error("  Restart failed — user systemd not reachable:")
                     for line in str(e).splitlines():
                         print(f"  {line}")
+                except SystemScopeRequiresRootError as e:
+                    # Defense in depth: the pre-check above should have
+                    # caught this, but a race (unit file appearing mid-run)
+                    # could still land here. Previously this exited the
+                    # whole wizard via sys.exit(1).
+                    print_error(f"  Restart failed: {e}")
+                    _print_system_scope_remediation("restart")
                 except Exception as e:
                     print_error(f"  Restart failed: {e}")
         elif service_installed:
-            if prompt_yes_no("  Start the gateway service?", True):
+            if supports_systemd and _system_scope_wizard_would_need_root():
+                _print_system_scope_remediation("start")
+            elif prompt_yes_no("  Start the gateway service?", True):
                 try:
                     if supports_systemd:
                         systemd_start()
@@ -2502,6 +2516,9 @@ def setup_gateway(config: dict):
                     print_error("  Start failed — user systemd not reachable:")
                     for line in str(e).splitlines():
                         print(f"  {line}")
+                except SystemScopeRequiresRootError as e:
+                    print_error(f"  Start failed: {e}")
+                    _print_system_scope_remediation("start")
                 except Exception as e:
                     print_error(f"  Start failed: {e}")
         elif supports_service_manager:
@@ -2529,6 +2546,9 @@ def setup_gateway(config: dict):
                             print_error("  Start failed — user systemd not reachable:")
                             for line in str(e).splitlines():
                                 print(f"  {line}")
+                        except SystemScopeRequiresRootError as e:
+                            print_error(f"  Start failed: {e}")
+                            _print_system_scope_remediation("start")
                         except Exception as e:
                             print_error(f"  Start failed: {e}")
                 except Exception as e:

hermes_cli/skin_engine.py

@@ -42,6 +42,7 @@ All fields are optional. Missing values inherit from the ``default`` skin.
       session_border: "#8B8682"          # Session ID dim color
       status_bar_bg: "#1a1a2e"          # TUI status/usage bar background
       voice_status_bg: "#1a1a2e"        # TUI voice status background
+      selection_bg: "#333355"           # TUI mouse-selection highlight background
       completion_menu_bg: "#1a1a2e"      # Completion menu background
       completion_menu_current_bg: "#333355"  # Active completion row background
       completion_menu_meta_bg: "#1a1a2e"     # Completion meta column background

hermes_cli/tools_config.py

@@ -308,6 +308,23 @@ TOOL_CATEGORIES = {
                     {"key": "SEARXNG_URL", "prompt": "Your SearXNG instance URL (e.g., http://localhost:8080)", "url": "https://searxng.github.io/searxng/"},
                 ],
             },
+            {
+                "name": "Brave Search (Free Tier)",
+                "badge": "free tier · search only",
+                "tag": "2,000 queries/mo free — search only (pair with any extract provider)",
+                "web_backend": "brave-free",
+                "env_vars": [
+                    {"key": "BRAVE_SEARCH_API_KEY", "prompt": "Brave Search subscription token", "url": "https://brave.com/search/api/"},
+                ],
+            },
+            {
+                "name": "DuckDuckGo (ddgs)",
+                "badge": "free · no key · search only",
+                "tag": "Search via the ddgs Python package — no API key (pair with any extract provider)",
+                "web_backend": "ddgs",
+                "env_vars": [],
+                "post_setup": "ddgs",
+            },
         ],
     },
     "image_gen": {
@@ -669,6 +686,32 @@ def _run_post_setup(post_setup_key: str):
         _print_info("    Full voice list: https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/VOICES.md")
         _print_info("    Switch voices by setting tts.piper.voice in ~/.hermes/config.yaml")
 
+    elif post_setup_key == "ddgs":
+        try:
+            __import__("ddgs")
+            _print_success("    ddgs is already installed")
+        except ImportError:
+            import subprocess
+            _print_info("    Installing ddgs (DuckDuckGo search package)...")
+            try:
+                result = subprocess.run(
+                    [sys.executable, "-m", "pip", "install", "-U", "ddgs", "--quiet"],
+                    capture_output=True, text=True, timeout=300,
+                )
+                if result.returncode == 0:
+                    _print_success("    ddgs installed")
+                else:
+                    _print_warning("    ddgs install failed:")
+                    _print_info(f"      {result.stderr.strip()[:300]}")
+                    _print_info("    Run manually: python -m pip install -U ddgs")
+                    return
+            except subprocess.TimeoutExpired:
+                _print_warning("    ddgs install timed out (>5min)")
+                _print_info("    Run manually: python -m pip install -U ddgs")
+                return
+        _print_info("    No API key required. DuckDuckGo enforces server-side rate limits.")
+        _print_info("    Pair with an extract provider if you also need web_extract.")
+
     elif post_setup_key == "spotify":
         # Run the full `hermes auth spotify` flow — if the user has no
         # client_id yet, this drops them into the interactive wizard

hermes_cli/voice.py

@@ -281,6 +281,8 @@ _recorder_lock = threading.Lock()
 # ── Continuous (VAD) state ───────────────────────────────────────────
 _continuous_lock = threading.Lock()
 _continuous_active = False
+_continuous_stopping = False
+_continuous_auto_restart: bool = True
 _continuous_recorder: Any = None
 
 # ── TTS-vs-STT feedback guard ────────────────────────────────────────
@@ -370,32 +372,43 @@ def start_continuous(
     on_silent_limit: Optional[Callable[[], None]] = None,
     silence_threshold: int = 200,
     silence_duration: float = 3.0,
-) -> None:
+    auto_restart: bool = True,
+) -> bool:
     """Start a VAD-driven continuous recording loop.
 
     The loop calls ``on_transcript(text)`` each time speech is detected and
-    transcribed successfully, then auto-restarts. After
-    ``_CONTINUOUS_NO_SPEECH_LIMIT`` consecutive silent cycles (no speech
-    picked up at all) the loop stops itself and calls ``on_silent_limit``
-    so the UI can reflect "voice off". Idempotent — calling while already
-    active is a no-op.
+    transcribed successfully. If ``auto_restart`` is True, it auto-restarts
+    for the next turn and resets the no-speech counter for that loop. If
+    ``auto_restart`` is False, the first silence-triggered transcription ends
+    the loop and reports ``"idle"``; no-speech counts are retained across
+    starts so a push-to-talk caller can still enforce the three-strikes guard.
+    After ``_CONTINUOUS_NO_SPEECH_LIMIT`` consecutive silent cycles (no speech
+    picked up at all) the loop stops itself and calls ``on_silent_limit`` so the
+    UI can reflect "voice off". Returns False if a previous stop is still
+    transcribing/cleaning up; otherwise returns True. Idempotent — calling while
+    already active is a successful no-op.
 
     ``on_status`` is called with ``"listening"`` / ``"transcribing"`` /
     ``"idle"`` so the UI can show a live indicator.
     """
-    global _continuous_active, _continuous_recorder
+    global _continuous_active, _continuous_recorder, _continuous_auto_restart
     global _continuous_on_transcript, _continuous_on_status, _continuous_on_silent_limit
     global _continuous_no_speech_count
 
     with _continuous_lock:
         if _continuous_active:
             _debug("start_continuous: already active — no-op")
-            return
+            return True
+        if _continuous_stopping:
+            _debug("start_continuous: stop/transcribe in progress — busy")
+            return False
         _continuous_active = True
+        _continuous_auto_restart = auto_restart
         _continuous_on_transcript = on_transcript
         _continuous_on_status = on_status
         _continuous_on_silent_limit = on_silent_limit
-        _continuous_no_speech_count = 0
+        if auto_restart:
+            _continuous_no_speech_count = 0
 
         if _continuous_recorder is None:
             _continuous_recorder = create_audio_recorder()
@@ -428,15 +441,18 @@ def start_continuous(
         except Exception:
             pass
 
+    return True
 
-def stop_continuous() -> None:
+
+def stop_continuous(force_transcribe: bool = False) -> None:
     """Stop the active continuous loop and release the microphone.
 
-    Idempotent — calling while not active is a no-op. Any in-flight
-    transcription completes but its result is discarded (the callback
-    checks ``_continuous_active`` before firing).
+    Idempotent — calling while not active is a no-op. If ``force_transcribe`` is
+    True, the recorder stops synchronously, then transcription/cleanup runs on a
+    background thread before reporting ``"idle"``. Otherwise the buffer is
+    discarded.
     """
-    global _continuous_active, _continuous_on_transcript
+    global _continuous_active, _continuous_on_transcript, _continuous_stopping
     global _continuous_on_status, _continuous_on_silent_limit
     global _continuous_recorder, _continuous_no_speech_count
 
@@ -446,18 +462,98 @@ def stop_continuous() -> None:
         _continuous_active = False
         rec = _continuous_recorder
         on_status = _continuous_on_status
+        on_transcript = _continuous_on_transcript
+        on_silent_limit = _continuous_on_silent_limit
+        auto_restart = _continuous_auto_restart
+        track_no_speech = force_transcribe and not auto_restart
+        _continuous_stopping = rec is not None
         _continuous_on_transcript = None
         _continuous_on_status = None
         _continuous_on_silent_limit = None
-        _continuous_no_speech_count = 0
+        if not track_no_speech:
+            _continuous_no_speech_count = 0
 
     if rec is not None:
-        try:
-            # cancel() (not stop()) discards buffered frames — the loop
-            # is over, we don't want to transcribe a half-captured turn.
-            rec.cancel()
-        except Exception as e:
-            logger.warning("failed to cancel recorder: %s", e)
+        if force_transcribe and on_transcript:
+            if on_status:
+                try:
+                    on_status("transcribing")
+                except Exception:
+                    pass
+            try:
+                wav_path = rec.stop()
+            except Exception as e:
+                logger.warning("failed to stop recorder: %s", e)
+                try:
+                    rec.cancel()
+                except Exception as cancel_error:
+                    logger.warning("failed to cancel recorder: %s", cancel_error)
+                wav_path = None
+
+            def _transcribe_and_cleanup():
+                global _continuous_no_speech_count, _continuous_stopping
+                transcript: Optional[str] = None
+                should_halt = False
+
+                try:
+                    if wav_path:
+                        try:
+                            result = transcribe_recording(wav_path)
+                            if result.get("success"):
+                                text = (result.get("transcript") or "").strip()
+                                if text and not is_whisper_hallucination(text):
+                                    transcript = text
+                        finally:
+                            if os.path.isfile(wav_path):
+                                os.unlink(wav_path)
+                except Exception as e:
+                    logger.warning("failed to stop/transcribe recorder: %s", e)
+                finally:
+                    if transcript:
+                        try:
+                            on_transcript(transcript)
+                        except Exception as e:
+                            logger.warning("on_transcript callback raised: %s", e)
+
+                    if track_no_speech:
+                        with _continuous_lock:
+                            if transcript:
+                                _continuous_no_speech_count = 0
+                            else:
+                                _continuous_no_speech_count += 1
+                                should_halt = (
+                                    _continuous_no_speech_count
+                                    >= _CONTINUOUS_NO_SPEECH_LIMIT
+                                )
+                                if should_halt:
+                                    _continuous_no_speech_count = 0
+                        if should_halt and on_silent_limit:
+                            try:
+                                on_silent_limit()
+                            except Exception:
+                                pass
+
+                    _play_beep(frequency=660, count=2)
+                    with _continuous_lock:
+                        _continuous_stopping = False
+                    if on_status:
+                        try:
+                            on_status("idle")
+                        except Exception:
+                            pass
+
+            threading.Thread(target=_transcribe_and_cleanup, daemon=True).start()
+            return
+        else:
+            try:
+                # cancel() (not stop()) discards buffered frames — the loop
+                # is over, we don't want to transcribe a half-captured turn.
+                rec.cancel()
+            except Exception as e:
+                logger.warning("failed to cancel recorder: %s", e)
+
+    with _continuous_lock:
+        _continuous_stopping = False
 
     # Audible "recording stopped" cue (CLI parity: same 660 Hz × 2 the
     # silence-auto-stop path plays).
@@ -603,23 +699,39 @@ def _continuous_on_silence() -> None:
                 _debug("_continuous_on_silence: stopped while waiting for TTS")
                 return
 
-    # Restart for the next turn.
-    _debug(f"_continuous_on_silence: restarting loop (no_speech={no_speech})")
-    _play_beep(frequency=880, count=1)
-    try:
-        rec.start(on_silence_stop=_continuous_on_silence)
-    except Exception as e:
-        logger.error("failed to restart continuous recording: %s", e)
-        _debug(f"_continuous_on_silence: restart raised {type(e).__name__}: {e}")
+    if _continuous_auto_restart:
+        # Restart for the next turn.
+        _debug(f"_continuous_on_silence: restarting loop (no_speech={no_speech})")
+        _play_beep(frequency=880, count=1)
+        try:
+            rec.start(on_silence_stop=_continuous_on_silence)
+        except Exception as e:
+            logger.error("failed to restart continuous recording: %s", e)
+            _debug(f"_continuous_on_silence: restart raised {type(e).__name__}: {e}")
+            with _continuous_lock:
+                _continuous_active = False
+            if on_status:
+                try:
+                    on_status("idle")
+                except Exception:
+                    pass
+            return
+
+        if on_status:
+            try:
+                on_status("listening")
+            except Exception:
+                pass
+    else:
+        # Do not auto-restart. Clean up state and notify idle.
+        _debug("_continuous_on_silence: auto_restart=False, stopping loop")
         with _continuous_lock:
             _continuous_active = False
-        return
-
-    if on_status:
-        try:
-            on_status("listening")
-        except Exception:
-            pass
+        if on_status:
+            try:
+                on_status("idle")
+            except Exception:
+                pass
 
 
 # ── TTS API ──────────────────────────────────────────────────────────

hermes_cli/web_server.py

@@ -55,7 +55,7 @@ from gateway.status import get_running_pid, read_runtime_status
 try:
     from fastapi import FastAPI, HTTPException, Request, WebSocket, WebSocketDisconnect
     from fastapi.middleware.cors import CORSMiddleware
-    from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
+    from fastapi.responses import FileResponse, HTMLResponse, JSONResponse, Response
     from fastapi.staticfiles import StaticFiles
     from pydantic import BaseModel
 except ImportError:
@@ -2109,8 +2109,8 @@ async def _start_device_code_flow(provider_id: str) -> Dict[str, Any]:
             name=f"oauth-codex-{sid[:6]}",
         ).start()
         # Block briefly until the worker has populated the user_code, OR error.
-        deadline = time.time() + 10
-        while time.time() < deadline:
+        deadline = time.monotonic() + 10
+        while time.monotonic() < deadline:
             with _oauth_sessions_lock:
                 s = _oauth_sessions.get(sid)
             if s and (s.get("user_code") or s["status"] != "pending"):
@@ -2244,10 +2244,10 @@ def _codex_full_login_worker(session_id: str) -> None:
             sess["expires_at"] = time.time() + sess["expires_in"]
 
         # Step 2: poll until authorized
-        deadline = time.time() + sess["expires_in"]
+        deadline = time.monotonic() + sess["expires_in"]
         code_resp = None
         with httpx.Client(timeout=httpx.Timeout(15.0)) as client:
-            while time.time() < deadline:
+            while time.monotonic() < deadline:
                 time.sleep(poll_interval)
                 poll = client.post(
                     f"{issuer}/api/accounts/deviceauth/token",
@@ -2405,6 +2405,83 @@ async def cancel_oauth_session(session_id: str, request: Request):
 # ---------------------------------------------------------------------------
 
 
+
+def _session_latest_descendant(session_id: str):
+    """Resolve a session id to the newest child leaf session.
+
+    /model may create child sessions. Dashboard refresh should continue the
+    newest child instead of reopening the old parent.
+    """
+    from hermes_state import SessionDB
+
+    def row_get(row, key, index):
+        if isinstance(row, dict):
+            return row.get(key)
+        try:
+            return row[key]
+        except Exception:
+            try:
+                return row[index]
+            except Exception:
+                return None
+
+    db = SessionDB()
+    try:
+        sid = db.resolve_session_id(session_id)
+        if not sid or not db.get_session(sid):
+            return None, []
+
+        conn = (
+            getattr(db, "conn", None)
+            or getattr(db, "_conn", None)
+            or getattr(db, "connection", None)
+            or getattr(db, "_connection", None)
+        )
+
+        rows = []
+        if conn is not None:
+            raw_rows = conn.execute(
+                "SELECT id, parent_session_id, started_at FROM sessions"
+            ).fetchall()
+            for row in raw_rows:
+                rows.append({
+                    "id": row_get(row, "id", 0),
+                    "parent_session_id": row_get(row, "parent_session_id", 1),
+                    "started_at": row_get(row, "started_at", 2),
+                })
+        else:
+            rows = db.list_sessions_rich(limit=10000, offset=0)
+
+        children = {}
+        for row in rows:
+            rid = row.get("id")
+            parent = row.get("parent_session_id")
+            if rid and parent:
+                children.setdefault(parent, []).append(row)
+
+        def started(row):
+            try:
+                return float(row.get("started_at") or 0)
+            except Exception:
+                return 0.0
+
+        current = sid
+        path = [sid]
+        seen = {sid}
+
+        while children.get(current):
+            candidates = [r for r in children[current] if r.get("id") not in seen]
+            if not candidates:
+                break
+            candidates.sort(key=started, reverse=True)
+            current = candidates[0]["id"]
+            path.append(current)
+            seen.add(current)
+
+        return current, path
+    finally:
+        db.close()
+
 @app.get("/api/sessions/{session_id}")
 async def get_session_detail(session_id: str):
     from hermes_state import SessionDB
@@ -2419,6 +2496,19 @@ async def get_session_detail(session_id: str):
         db.close()
 
 
+
+@app.get("/api/sessions/{session_id}/latest-descendant")
+async def get_session_latest_descendant(session_id: str):
+    latest, path = _session_latest_descendant(session_id)
+    if not latest:
+        raise HTTPException(status_code=404, detail="Session not found")
+    return {
+        "requested_session_id": path[0] if path else session_id,
+        "session_id": latest,
+        "path": path,
+        "changed": bool(path and latest != path[0]),
+    }
+
 @app.get("/api/sessions/{session_id}/messages")
 async def get_session_messages(session_id: str):
     from hermes_state import SessionDB
@@ -2620,6 +2710,7 @@ async def delete_cron_job(job_id: str):
 class ProfileCreate(BaseModel):
     name: str
     clone_from_default: bool = False
+    no_skills: bool = False
 
 
 class ProfileRename(BaseModel):
@@ -2725,11 +2816,13 @@ async def create_profile_endpoint(body: ProfileCreate):
             name=body.name,
             clone_from="default" if body.clone_from_default else None,
             clone_config=body.clone_from_default,
+            no_skills=body.no_skills,
         )
         # Match the CLI's profile-create flow: fresh named profiles get the
         # bundled skills installed. When cloning from default, create_profile()
         # has already copied the source profile's skills, including any
-        # user-installed skills.
+        # user-installed skills. When no_skills=True, create_profile() wrote
+        # the opt-out marker and seed_profile_skills() will no-op.
         if not body.clone_from_default:
             profiles_mod.seed_profile_skills(path, quiet=True)
 
@@ -3200,8 +3293,18 @@ def _resolve_chat_argv(
     argv, cwd = _make_tui_argv(PROJECT_ROOT / "ui-tui", tui_dev=False)
     env = os.environ.copy()
     env.setdefault("NODE_ENV", "production")
+    # Browser-embedded chat should prefer stable wheel-based scrollback over
+    # native terminal mouse tracking. When mouse tracking is enabled, wheel
+    # events are consumed by the TUI and forwarded as terminal input, which
+    # makes browser-side transcript scrolling feel broken. Keep the terminal
+    # build unchanged for native CLI usage; only disable mouse tracking for
+    # the dashboard PTY path.
+    env.setdefault("HERMES_TUI_DISABLE_MOUSE", "1")
 
     if resume:
+        latest_resume, _latest_path = _session_latest_descendant(resume)
+        if latest_resume:
+            resume = latest_resume
         env["HERMES_TUI_RESUME"] = resume
 
     if sidecar_url:
@@ -3459,12 +3562,42 @@ async def events_ws(ws: WebSocket) -> None:
                     _event_channels.pop(channel, None)
 
 
+def _normalise_prefix(raw: Optional[str]) -> str:
+    """Normalise an X-Forwarded-Prefix header value.
+
+    Returns a string like ``"/hermes"`` (no trailing slash) or ``""`` when
+    no prefix is set / the header is malformed. We deliberately reject
+    anything containing ``..`` or non-printable bytes so a hostile proxy
+    can't inject HTML via the prefix.
+    """
+    if not raw:
+        return ""
+    p = raw.strip()
+    if not p:
+        return ""
+    if not p.startswith("/"):
+        p = "/" + p
+    p = p.rstrip("/")
+    if "//" in p or ".." in p or any(c in p for c in ('"', "'", "<", ">", " ", "\n", "\r", "\t")):
+        return ""
+    if len(p) > 64:
+        return ""
+    return p
+
+
 def mount_spa(application: FastAPI):
     """Mount the built SPA. Falls back to index.html for client-side routing.
 
     The session token is injected into index.html via a ``<script>`` tag so
     the SPA can authenticate against protected API endpoints without a
     separate (unauthenticated) token-dispensing endpoint.
+
+    When served behind a path-prefix reverse proxy (e.g.
+    ``mission-control.tilos.com/hermes/*`` -> local Caddy -> :9119), the
+    proxy injects ``X-Forwarded-Prefix: /hermes`` on every request. We
+    rewrite the served ``index.html`` so absolute asset URLs (``/assets/...``)
+    and the SPA's runtime ``__HERMES_BASE_PATH__`` honour that prefix
+    without rebuilding the bundle.
     """
     if not WEB_DIST.exists():
         @application.get("/{full_path:path}")
@@ -3477,24 +3610,62 @@ def mount_spa(application: FastAPI):
 
     _index_path = WEB_DIST / "index.html"
 
-    def _serve_index():
-        """Return index.html with the session token injected."""
+    def _serve_index(prefix: str = ""):
+        """Return index.html with the session token + base-path injected.
+
+        ``prefix`` is the normalised ``X-Forwarded-Prefix`` (e.g. ``/hermes``)
+        or empty string when served at root.
+        """
         html = _index_path.read_text()
         chat_js = "true" if _DASHBOARD_EMBEDDED_CHAT_ENABLED else "false"
         token_script = (
             f'<script>window.__HERMES_SESSION_TOKEN__="{_SESSION_TOKEN}";'
-            f"window.__HERMES_DASHBOARD_EMBEDDED_CHAT__={chat_js};</script>"
+            f"window.__HERMES_DASHBOARD_EMBEDDED_CHAT__={chat_js};"
+            f'window.__HERMES_BASE_PATH__="{prefix}";</script>'
         )
+        if prefix:
+            # Rewrite absolute asset URLs baked into the Vite build so the
+            # browser fetches them through the same proxy prefix.
+            html = html.replace('href="/assets/', f'href="{prefix}/assets/')
+            html = html.replace('src="/assets/', f'src="{prefix}/assets/')
+            html = html.replace('href="/favicon.ico"', f'href="{prefix}/favicon.ico"')
+            html = html.replace('href="/fonts/', f'href="{prefix}/fonts/')
+            html = html.replace('href="/ds-assets/', f'href="{prefix}/ds-assets/')
+            html = html.replace('src="/ds-assets/', f'src="{prefix}/ds-assets/')
         html = html.replace("</head>", f"{token_script}</head>", 1)
         return HTMLResponse(
             html,
             headers={"Cache-Control": "no-store, no-cache, must-revalidate"},
         )
 
+    # When served behind a path-prefix proxy, the built CSS contains
+    # absolute ``url(/fonts/...)`` and ``url(/ds-assets/...)`` references.
+    # Browsers resolve those against the document origin, which means
+    # under ``/hermes`` they'd hit ``mission-control.tilos.com/fonts/...``
+    # (the MC Pages app), not the Hermes backend. Intercept CSS asset
+    # requests BEFORE the StaticFiles mount and rewrite the absolute paths
+    # when a prefix is in play.
+    @application.get("/assets/{filename}.css")
+    async def serve_css(filename: str, request: Request):
+        css_path = WEB_DIST / "assets" / f"{filename}.css"
+        if not css_path.is_file() or not css_path.resolve().is_relative_to(
+            WEB_DIST.resolve()
+        ):
+            return JSONResponse({"error": "not found"}, status_code=404)
+        prefix = _normalise_prefix(request.headers.get("x-forwarded-prefix"))
+        css = css_path.read_text()
+        if prefix:
+            for asset_dir in ("/fonts/", "/fonts-terminal/", "/ds-assets/", "/assets/"):
+                css = css.replace(f"url({asset_dir}", f"url({prefix}{asset_dir}")
+                css = css.replace(f"url(\"{asset_dir}", f"url(\"{prefix}{asset_dir}")
+                css = css.replace(f"url('{asset_dir}", f"url('{prefix}{asset_dir}")
+        return Response(content=css, media_type="text/css")
+
     application.mount("/assets", StaticFiles(directory=WEB_DIST / "assets"), name="assets")
 
     @application.get("/{full_path:path}")
-    async def serve_spa(full_path: str):
+    async def serve_spa(full_path: str, request: Request):
+        prefix = _normalise_prefix(request.headers.get("x-forwarded-prefix"))
         file_path = WEB_DIST / full_path
         # Prevent path traversal via url-encoded sequences (%2e%2e/)
         if (
@@ -3504,7 +3675,7 @@ def mount_spa(application: FastAPI):
             and file_path.is_file()
         ):
             return FileResponse(file_path)
-        return _serve_index()
+        return _serve_index(prefix)
 
 
 # ---------------------------------------------------------------------------