fix(hwfit): validate remote SSH detection targets (#3718)

routes/cookbook_routes.py

@@ -19,6 +19,7 @@ from src.constants import COOKBOOK_STATE_FILE
 from pydantic import BaseModel
 
 from core.middleware import require_admin
+from routes._validators import validate_remote_host, validate_ssh_port
 from core.platform_compat import (
     IS_WINDOWS,
     detached_popen_kwargs,
@@ -33,9 +34,8 @@ from routes.shell_routes import TMUX_LOG_DIR
 logger = logging.getLogger(__name__)
 
 from routes.cookbook_helpers import (
-    _SSH_PORT_RE, _REMOTE_HOST_RE, _SESSION_ID_RE,
-    _validate_repo_id, _validate_serve_model_id, _validate_include, _validate_remote_host, _validate_token,
-    _validate_local_dir, _validate_ssh_port, _validate_gpus, _shell_path,
+    _SESSION_ID_RE, _validate_repo_id, _validate_serve_model_id, _validate_include, _validate_token,
+    _validate_local_dir, _validate_gpus, _shell_path,
     _ps_squote, _bash_squote, _validate_serve_cmd, _parse_serve_phase,
     _safe_env_prefix, _local_tooling_path_export, _append_serve_preflight_exit_lines,
     _append_serve_exit_code_lines, _append_llama_cpp_linux_accel_build_lines, _cached_model_scan_script,
@@ -407,8 +407,8 @@ def setup_cookbook_routes() -> APIRouter:
         else:
             _validate_repo_id(req.repo_id)
             _validate_include(req.include)
-        _validate_remote_host(req.remote_host)
-        req.ssh_port = _validate_ssh_port(req.ssh_port)
+        validate_remote_host(req.remote_host)
+        req.ssh_port = validate_ssh_port(req.ssh_port)
         req.local_dir = _validate_local_dir(req.local_dir)
         req.hf_token = "" if is_ollama_download else (req.hf_token or _load_stored_hf_token())
         _validate_token(req.hf_token)
@@ -739,9 +739,8 @@ def setup_cookbook_routes() -> APIRouter:
         # Validate shell-bound inputs, matching the sibling list_gpus endpoint —
         # `host`/`ssh_port` are interpolated into an ssh command below, so an
         # unvalidated value (e.g. "x'; rm -rf ~ #") would be command injection.
-        host = _validate_remote_host(host)
-        if ssh_port is not None and ssh_port != "" and not _SSH_PORT_RE.fullmatch(ssh_port):
-            raise HTTPException(400, "Invalid ssh_port")
+        host = validate_remote_host(host)
+        ssh_port = validate_ssh_port(ssh_port)
         TMUX_LOG_DIR.mkdir(parents=True, exist_ok=True)
 
         model_dirs = []
@@ -890,11 +889,16 @@ def setup_cookbook_routes() -> APIRouter:
             # listening" check without requiring ss/netstat/nmap.
             ssh_base = ["ssh", "-o", "ConnectTimeout=4", "-o", "StrictHostKeyChecking=no"]
             if ssh_port and str(ssh_port) != "22":
-                if not _SSH_PORT_RE.match(str(ssh_port)):
+                try:
+                    ssh_port = validate_ssh_port(ssh_port)
+                except HTTPException:
                     return None
                 ssh_base.extend(["-p", str(ssh_port)])
-            host_arg = remote
-            if not _REMOTE_HOST_RE.match(host_arg):
+            try:
+                host_arg = validate_remote_host(remote)
+            except HTTPException:
+                return None
+            if not host_arg:
                 return None
             probe_ports = " ".join(str(start_port + i) for i in range(max_offset + 1))
             script = (
@@ -1197,8 +1201,8 @@ def setup_cookbook_routes() -> APIRouter:
         """
         require_admin(request)
         # Defence-in-depth: reject values that could break out of shell contexts.
-        _validate_remote_host(req.remote_host)
-        req.ssh_port = _validate_ssh_port(req.ssh_port)
+        validate_remote_host(req.remote_host)
+        req.ssh_port = validate_ssh_port(req.ssh_port)
         req.gpus = _validate_gpus(req.gpus)
         req.hf_token = req.hf_token or _load_stored_hf_token()
         _validate_token(req.hf_token)
@@ -1638,12 +1642,11 @@ def setup_cookbook_routes() -> APIRouter:
     async def server_setup(request: Request, req: SetupRequest):
         """Install required dependencies on a remote server via SSH."""
         require_admin(request)
-        host = _validate_remote_host(req.host)
+        host = validate_remote_host(req.host)
         if not host:
             raise HTTPException(400, "host is required")
         port = req.ssh_port
-        if port is not None and port != "" and not re.fullmatch(r"\d{1,5}", port):
-            raise HTTPException(400, "Invalid ssh_port")
+        port = validate_ssh_port(port)
         pf = f"-p {port} " if port and port != "22" else ""
 
         # Detect platform: Windows first (echo %OS% → Windows_NT), then Termux, then Linux
@@ -1887,9 +1890,8 @@ def setup_cookbook_routes() -> APIRouter:
         `busy` is True when free_mb/total_mb < 0.5.
         """
         require_admin(request)
-        host = _validate_remote_host(host)
-        if ssh_port is not None and ssh_port != "" and not _SSH_PORT_RE.fullmatch(ssh_port):
-            raise HTTPException(400, "Invalid ssh_port")
+        host = validate_remote_host(host)
+        ssh_port = validate_ssh_port(ssh_port)
         gpu_query = "nvidia-smi --query-gpu=index,name,memory.free,memory.total,memory.used,utilization.gpu,uuid --format=csv,noheader,nounits"
         nvidia_error = None
         try:
@@ -2046,9 +2048,8 @@ def setup_cookbook_routes() -> APIRouter:
         sig = (req.signal or "TERM").upper()
         if sig not in ("TERM", "KILL", "INT"):
             raise HTTPException(400, "signal must be TERM, KILL, or INT")
-        host = _validate_remote_host(req.host)
-        if req.ssh_port and not _SSH_PORT_RE.fullmatch(req.ssh_port):
-            raise HTTPException(400, "Invalid ssh_port")
+        host = validate_remote_host(req.host)
+        req.ssh_port = validate_ssh_port(req.ssh_port)
         kill_cmd = f"kill -{sig} {req.pid}"
         try:
             if host:
@@ -2382,14 +2383,19 @@ def setup_cookbook_routes() -> APIRouter:
             host = (srv.get("host") or "").strip()
             if not host:
                 continue  # local-only entry; the /proc scan handles it
-            if not _REMOTE_HOST_RE.match(host):
+            try:
+                host = validate_remote_host(host)
+            except HTTPException:
                 continue
             sport = str(srv.get("port") or "").strip()
             ssh_base = ["ssh", "-o", "ConnectTimeout=4", "-o", "StrictHostKeyChecking=no"]
             if sport and sport != "22":
-                if not _SSH_PORT_RE.match(sport):
+                try:
+                    sport = validate_ssh_port(sport)
+                except HTTPException:
                     continue
-                ssh_base.extend(["-p", sport])
+                if sport != "22":
+                    ssh_base.extend(["-p", sport])
 
             try:
                 ls = subprocess.run(
@@ -2743,12 +2749,18 @@ def setup_cookbook_routes() -> APIRouter:
             if not _SESSION_ID_RE.match(session_id):
                 logger.warning(f"Skipping task with unsafe session_id: {session_id!r}")
                 continue
-            if remote and not _REMOTE_HOST_RE.match(remote):
-                logger.warning(f"Skipping task with unsafe remoteHost: {remote!r}")
-                continue
-            if _tport and not _SSH_PORT_RE.match(str(_tport)):
-                logger.warning(f"Skipping task with unsafe sshPort: {_tport!r}")
-                continue
+            if remote:
+                try:
+                    remote = validate_remote_host(remote)
+                except HTTPException:
+                    logger.warning(f"Skipping task with unsafe remoteHost: {remote!r}")
+                    continue
+            if _tport:
+                try:
+                    _tport = validate_ssh_port(str(_tport))
+                except HTTPException:
+                    logger.warning(f"Skipping task with unsafe sshPort: {_tport!r}")
+                    continue
             if task_platform == "windows" and remote:
                 # Windows: check PID file + Get-Process, read log tail
                 sd = "$env:TEMP\\odysseus-sessions"